Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms related to scientific methods and experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Agreement between simulation/theory and experiment

    np_acts-logits-general · gemini-2.0-flash

    agreement with simulations or experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MediatR
    -0.54
    triangleq
    -0.52
    strix
    -0.46
    ngdoc
    -0.45
     kult
    -0.43
    исленность
    -0.42
     ***!
    -0.42
    randrange
    -0.42
    ándome
    -0.41
    cef
    -0.41
    POSITIVE LOGITS
     agreement
    1.05
     predictions
    0.92
    agreement
    0.86
     agree
    0.85
     Agreement
    0.84
     agrees
    0.82
     disagreement
    0.82
    Agreement
    0.81
     experimentally
    0.81
     reproduces
    0.81
    Act Density 2.135%

    No Known Activations