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

    Neuronpedia

    INDEX
    Explanations

    conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    分级
    -0.07
    вет
    -0.07
    ינוי
    -0.07
    xBB
    -0.06
    급
    -0.06
     �
    -0.06
    행
    -0.06
    ア
    -0.06
    脂
    -0.06
     väl
    -0.06
    POSITIVE LOGITS
     ф
    0.07
     loggedIn
    0.07
    _px
    0.07
     צריכ
    0.07
    ENDED
    0.07
     base
    0.07
    累计
    0.07
    💞
    0.07
    毫无疑
    0.07
    ڃ
    0.06
    Act Density 0.000%

    No Known Activations