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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rl
    -0.08
    cole
    -0.07
    먼
    -0.07
    Goal
    -0.07
    kind
    -0.07
    venge
    -0.07
    anya
    -0.07
    ناق
    -0.07
    .cv
    -0.07
    _billing
    -0.06
    POSITIVE LOGITS
    途径
    0.07
     נדרש
    0.07
    认识到
    0.07
     ścian
    0.07
     gratuito
    0.06
     reported
    0.06
     zeigen
    0.06
     يجعل
    0.06
    עוב
    0.06
     Louisville
    0.06
    Act Density 0.003%

    No Known Activations