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

    Neuronpedia

    INDEX
    Explanations

    administrator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ثن
    -0.07
     Чер
    -0.06
    اختبار
    -0.06
    [df
    -0.06
    ическим
    -0.06
    "These
    -0.06
    ackBar
    -0.06
    time
    -0.06
    	body
    -0.06
    ⭕
    -0.06
    POSITIVE LOGITS
    窎
    0.07
    -------↵
    0.07
    ając
    0.07
    走到
    0.07
    ערכת
    0.06
    ㌃
    0.06
    会引起
    0.06
    麽
    0.06
    年起
    0.06
    rbrace
    0.06
    Act Density 0.009%

    No Known Activations