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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liste
    -0.06
     myš
    -0.06
     smash
    -0.06
     Whe
    -0.06
     ув
    -0.06
     który
    -0.06
    阳城
    -0.06
    .coeff
    -0.06
     то
    -0.06
    τη
    -0.06
    POSITIVE LOGITS
    [Z
    0.06
    ynchron
    0.06
     genitals
    0.06
    .FindAsync
    0.06
    poons
    0.06
     Anglic
    0.06
    anguages
    0.06
    dg
    0.05
    "data
    0.05
     міг
    0.05
    Act Density 0.000%

    No Known Activations