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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -с
    -0.07
    ')['
    -0.07
    donnees
    -0.06
     Spit
    -0.06
    istring
    -0.06
     scared
    -0.06
    щин
    -0.06
    ust
    -0.06
    -master
    -0.06
    cie
    -0.06
    POSITIVE LOGITS
    .Warn
    0.07
    .Article
    0.07
    alli
    0.06
    rol
    0.06
     collision
    0.06
     BLACK
    0.06
     AFF
    0.06
     Tap
    0.06
    AYS
    0.06
    กฎ
    0.06
    Act Density 0.000%

    No Known Activations