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

    Neuronpedia

    INDEX
    Explanations

    during

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Justiça
    -0.08
     justice
    -0.07
     convenience
    -0.07
     Health
    -0.07
     arma
    -0.07
     Ведь
    -0.07
    _ctx
    -0.06
     Justice
    -0.06
     Good
    -0.06
    Hen
    -0.06
    POSITIVE LOGITS
    反弹
    0.08
     antioxidant
    0.07
    _reporting
    0.07
    UTURE
    0.07
    getItem
    0.07
    .CONT
    0.07
    培养
    0.06
    .walk
    0.06
     לת
    0.06
    سين
    0.06
    Act Density 0.041%

    No Known Activations