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

    Neuronpedia

    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'int
    -0.07
    Resultado
    -0.06
     Writing
    -0.06
     जनत
    -0.06
     国
    -0.06
    �
    -0.06
    итет
    -0.06
     subs
    -0.06
     пан
    -0.06
     bother
    -0.06
    POSITIVE LOGITS
     average
    0.07
     treat
    0.07
    ایند
    0.07
    -low
    0.07
     reserv
    0.06
    )((
    0.06
     implant
    0.06
    URRENT
    0.06
     ((_
    0.06
    込
    0.06
    Act Density 0.004%

    No Known Activations