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

    Neuronpedia

    INDEX
    Explanations

    align, center

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toda
    -0.07
     информ
    -0.07
    zion
    -0.06
    _VALIDATE
    -0.06
    뙝
    -0.06
     مجاني
    -0.06
     convened
    -0.06
    unicipio
    -0.06
    _F
    -0.06
    edula
    -0.06
    POSITIVE LOGITS
    FLOW
    0.08
    落后
    0.06
    Cargo
    0.06
    背上
    0.06
     Nit
    0.06
    -password
    0.06
    _listing
    0.06
    嫌疑人
    0.06
     Indust
    0.06
     بطريقة
    0.06
    Act Density 0.021%

    No Known Activations