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

    Neuronpedia

    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STYLE
    -0.07
    不足
    -0.07
    adecimal
    -0.06
    /style
    -0.06
    _style
    -0.06
    もない
    -0.06
    .loc
    -0.06
     Lond
    -0.06
    .users
    -0.06
    .LOGIN
    -0.06
    POSITIVE LOGITS
    运
    0.07
    renal
    0.06
    quette
    0.06
    comm
    0.06
    initWith
    0.06
     referees
    0.06
     корм
    0.06
     colle
    0.06
     dipping
    0.06
     Class
    0.06
    Act Density 0.006%

    No Known Activations