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

    Neuronpedia

    INDEX
    Explanations

    sports commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    _ATTACK
    -0.07
     Tobacco
    -0.07
    ":{"
    -0.06
    (tcp
    -0.06
     blames
    -0.06
    чого
    -0.06
    -0.06
    (Socket
    -0.06
     ژانویه
    -0.06
    POSITIVE LOGITS
     partir
    0.06
    467
    0.06
     GENER
    0.06
    contador
    0.06
     Ná
    0.05
    Issues
    0.05
    لح
    0.05
    pte
    0.05
    jack
    0.05
    defer
    0.05
    Act Density 0.009%

    No Known Activations