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

    Neuronpedia

    INDEX
    Explanations

    question/answer pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satisfied
    0.84
    Glasses
    0.76
    b
    0.75
     persuas
    0.73
     binders
    0.71
     Peres
    0.71
     understood
    0.71
     beverage
    0.70
     mero
    0.70
     dressed
    0.70
    POSITIVE LOGITS
    いち
    0.88
    exitTool
    0.77
     راه
    0.76
    ł
    0.73
     fă
    0.72
     época
    0.70
    getUrl
    0.70
     estrict
    0.70
     genética
    0.68
    iczne
    0.68
    Act Density 0.016%

    No Known Activations