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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain numerical values or instructions involving conditionality

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

    Code snippets and English/foreign language mix

    np_acts-logits-general · gemini-2.0-flash

    Star Wars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.69
     portanto
    -0.63
    Cursors
    -0.61
    Initializable
    -0.57
    windowFixed
    -0.56
     Tengo
    -0.55
    bootstrapcdn
    -0.53
    WebVitals
    -0.52
     perdió
    -0.52
     nahilalakip
    -0.51
    POSITIVE LOGITS
     latter
    0.66
     main
    0.65
    "]);
    0.59
    "])
    0.58
     }}"></
    0.56
    ">'+
    0.56
    ajā
    0.56
    ">',
    0.55
    iffion
    0.55
    之所以
    0.55
    Act Density 0.020%

    No Known Activations