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

    Neuronpedia

    INDEX
    Explanations

    Python programming constructs and return statements

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

    Code snippets and unusual punctuation/symbols

    np_acts-logits-general · gemini-2.0-flash

    French male cyclists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    -0.81
    :
    -0.58
    TagHelpers
    -0.56
    :</
    -0.56
    :(
    -0.52
     :
    -0.51
    ology
    -0.48
     or
    -0.48
     may
    -0.46
     civil
    -0.46
    POSITIVE LOGITS
     purpoſe
    0.91
     houſe
    0.84
     quæ
    0.83
     myſelf
    0.82
     ſeveral
    0.82
     pleaſure
    0.81
     uſe
    0.79
     Monfieur
    0.78
     itſelf
    0.76
     ſtate
    0.76
    Act Density 0.026%

    No Known Activations