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

    Neuronpedia

    INDEX
    Explanations

    /licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    冷冻
    -0.07
     continua
    -0.07
     wildcard
    -0.07
    两位
    -0.07
    fecha
    -0.07
     zombie
    -0.07
     Alexander
    -0.07
    腿部
    -0.07
     aby
    -0.07
    万名
    -0.07
    POSITIVE LOGITS
    نع
    0.07
     breeze
    0.07
     food
    0.07
    ម
    0.07
     מח
    0.06
     ministry
    0.06
    黼
    0.06
    많
    0.06
     עבוד
    0.06
     chứng
    0.06
    Act Density 0.000%

    No Known Activations