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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methodologies and parameters in research

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

    Citations or references (year) with volume/issue numbers

    np_acts-logits-general · gemini-2.0-flash

    citation punctuation or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     according
    -0.60
     spender
    -0.58
    usermodel
    -0.58
     通常
    -0.56
    Sadly
    -0.55
    TabIndex
    -0.55
     estes
    -0.54
    setViewportView
    -0.54
     astronomer
    -0.54
     hopefully
    -0.53
    POSITIVE LOGITS
     The
    0.88
     Comparison
    0.77
     Effects
    0.74
     Effect
    0.74
     An
    0.73
     influence
    0.72
     Influence
    0.71
    Influence
    0.70
     comparison
    0.70
     Einfluß
    0.69
    Act Density 0.378%

    No Known Activations