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

    Neuronpedia

    INDEX
    Explanations

    ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    裝
    -0.07
    designation
    -0.07
    被骗
    -0.07
    NPC
    -0.07
    uan
    -0.07
    hai
    -0.07
    턱
    -0.07
    :"",↵
    -0.07
    考え
    -0.07
     אלפי
    -0.07
    POSITIVE LOGITS
     inconsistencies
    0.07
     aynı
    0.07
    .bunifu
    0.07
    redient
    0.06
     مؤ
    0.06
    ɞ
    0.06
     abortion
    0.06
     questo
    0.06
    .combine
    0.06
    质地
    0.06
    Act Density 0.004%

    No Known Activations