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

    Neuronpedia

    INDEX
    Explanations

    availability or presence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     месяцев
    -0.08
     сох
    -0.07
     минут
    -0.07
     модели
    -0.07
     IGNORE
    -0.07
     قال
    -0.07
    🐼
    -0.07
    UNT
    -0.07
    的要求
    -0.07
    _mux
    -0.07
    POSITIVE LOGITS
    햊
    0.07
    清单
    0.07
    馉
    0.07
    osaic
    0.07
    �
    0.06
    oldemort
    0.06
    .Mode
    0.06
    [parent
    0.06
     }));↵
    0.06
    售卖
    0.06
    Act Density 0.036%

    No Known Activations