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

    Neuronpedia

    INDEX
    Explanations

    discussions centered around medical diagnostics and treatment

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

    Punctuation marks and common connecting words

    np_acts-logits-general · gemini-2.0-flash

    following explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wtf
    -0.56
     WTF
    -0.53
    wtf
    -0.47
    <?>
    -0.46
     IMO
    -0.46
     imo
    -0.45
    WTF
    -0.44
     Caul
    -0.43
    :"",
    -0.42
    😤
    -0.41
    POSITIVE LOGITS
    parsedMessage
    1.02
     समीक्षाओं
    0.73
     nakalista
    0.72
    enumii
    0.70
     IndexPath
    0.69
     mikrofon
    0.69
    InjectAttribute
    0.69
    PerformLayout
    0.68
    __*/
    0.67
     unmute
    0.65
    Act Density 0.071%

    No Known Activations