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

    Neuronpedia

    INDEX
    Explanations

    USE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    凌晨
    -0.07
     mills
    -0.07
    十年前
    -0.07
     Constitutional
    -0.07
    教堂
    -0.07
    ⇛
    -0.07
    男朋友
    -0.07
    Bell
    -0.07
    @Component
    -0.06
    etr
    -0.06
    POSITIVE LOGITS
    .resp
    0.07
     antibody
    0.07
    .gray
    0.06
    老年
    0.06
    (total
    0.06
    Projectile
    0.06
    movie
    0.06
    .Match
    0.06
    _active
    0.06
    .Ab
    0.06
    Act Density 0.002%

    No Known Activations