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

    Neuronpedia

    INDEX
    Explanations

    anything

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    푸
    -0.08
    ых
    -0.07
    _PUBLIC
    -0.07
     inspectors
    -0.07
    เอ
    -0.07
    גרפי
    -0.07
    dif
    -0.07
    齿
    -0.07
    ══
    -0.07
     sóng
    -0.07
    POSITIVE LOGITS
    	string
    0.07
    Overall
    0.07
    numero
    0.07
    Ῠ
    0.07
    (INPUT
    0.07
    upil
    0.06
    (attribute
    0.06
     There
    0.06
     cidade
    0.06
    收盘
    0.06
    Act Density 0.005%

    No Known Activations