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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scared
    -0.07
     sez
    -0.07
    ]!='
    -0.07
     śc
    -0.07
    蒯
    -0.07
     trapped
    -0.07
    假期
    -0.07
    :update
    -0.07
     prez
    -0.06
    ƨ
    -0.06
    POSITIVE LOGITS
    effects
    0.07
    移动端
    0.07
    /vendors
    0.07
    _attributes
    0.07
     благ
    0.07
    alendar
    0.07
     הראשונים
    0.07
    /material
    0.07
    ;</
    0.07
    .enemy
    0.07
    Act Density 0.006%

    No Known Activations