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

    Neuronpedia

    INDEX
    Explanations

    complex scientific expressions and equations

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

    Mathematical/scientific notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    chemical and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ridge
    -0.73
     Healey
    -0.73
     Zet
    -0.69
     Kiki
    -0.69
    Ridge
    -0.68
     Bentley
    -0.65
     Heber
    -0.64
     Coh
    -0.63
     Mille
    -0.62
     RIDGE
    -0.62
    POSITIVE LOGITS
     Lovell
    0.93
    Tro
    0.75
     Christina
    0.70
     Trophy
    0.69
     Worthington
    0.69
    Christina
    0.68
     Radford
    0.67
     Tro
    0.67
     tro
    0.66
     LOD
    0.64
    Act Density 0.668%

    No Known Activations