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

    Neuronpedia

    INDEX
    Explanations

    keywords and topical structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    widget
    0.47
    Interpol
    0.46
    ol
    0.45
    Val
    0.44
    æs
    0.44
    tool
    0.43
    ツール
    0.42
    ст
    0.42
    inj
    0.42
    Matched
    0.41
    POSITIVE LOGITS
     Patriots
    0.47
     infect
    0.46
     infek
    0.45
     varieties
    0.45
     vanadium
    0.44
     infected
    0.44
     slogans
    0.43
     keywords
    0.43
    цтва
    0.42
     javascript
    0.41
    Act Density 0.002%

    No Known Activations