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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alonso
    -0.07
    �
    -0.07
    中含有
    -0.07
    persist
    -0.07
    _authentication
    -0.07
     substitution
    -0.07
    extends
    -0.07
    (null
    -0.07
     Typically
    -0.07
     Desmond
    -0.07
    POSITIVE LOGITS
    IVEN
    0.06
    嗯
    0.06
     laying
    0.06
    奶油
    0.06
     gauge
    0.06
     организация
    0.06
    價格
    0.06
     anche
    0.06
     ash
    0.06
    ễ
    0.06
    Act Density 0.014%

    No Known Activations