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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ils
    -0.07
     Khi
    -0.06
     florida
    -0.06
    Compat
    -0.06
    amine
    -0.06
     ном
    -0.06
    ляются
    -0.06
    on
    -0.06
     Ella
    -0.06
     Falcons
    -0.06
    POSITIVE LOGITS
    lify
    0.07
    Các
    0.07
     INC
    0.07
    ῆς
    0.06
    REF
    0.06
    (()=>{↵
    0.06
    .gb
    0.06
    さ
    0.06
    漂
    0.06
    ']]
    0.06
    Act Density 0.053%

    No Known Activations