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

    Neuronpedia

    INDEX
    Explanations

    exposure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    POP
    -0.07
     Borders
    -0.06
    онов
    -0.06
    WXYZ
    -0.06
    γη
    -0.06
     �
    -0.06
    ONA
    -0.06
     мет
    -0.06
     BOX
    -0.06
    Loss
    -0.06
    POSITIVE LOGITS
     mktime
    0.08
     mr
    0.07
    ��
    0.06
     стоимость
    0.06
     đị
    0.06
    ects
    0.06
    _kind
    0.06
    ilogue
    0.06
     Accessed
    0.06
    	E
    0.06
    Act Density 0.013%

    No Known Activations