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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Furious
    -0.07
    WITH
    -0.07
    ичні
    -0.07
    -American
    -0.06
     RUS
    -0.06
    ارية
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
     simplement
    -0.06
     терап
    -0.06
     CONNECTION
    -0.06
    POSITIVE LOGITS
    EH
    0.06
     piled
    0.06
    견
    0.06
    riminator
    0.06
    があり
    0.06
    湿
    0.06
    imm
    0.06
     grandson
    0.06
    ’d
    0.06
     KV
    0.06
    Act Density 0.042%

    No Known Activations