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

    Neuronpedia

    INDEX
    Explanations

    non

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ஓ
    -0.07
     nationally
    -0.07
    (strategy
    -0.07
    ✉
    -0.07
    among
    -0.07
    心理
    -0.07
    ♉
    -0.07
    跳
    -0.06
    ⒡
    -0.06
    .centerX
    -0.06
    POSITIVE LOGITS
    مواف
    0.08
     replacing
    0.08
    造假
    0.07
    regor
    0.07
    劄
    0.07
    defined
    0.07
     seront
    0.07
    werp
    0.06
    後來
    0.06
    quee
    0.06
    Act Density 0.001%

    No Known Activations