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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Activity
    -0.07
     Emin
    -0.06
    透
    -0.06
     ADC
    -0.06
    İTESİ
    -0.06
    stakes
    -0.06
    _yaw
    -0.06
     أر
    -0.06
    ुख
    -0.06
    ']));
    -0.06
    POSITIVE LOGITS
    .bid
    0.07
    _likelihood
    0.07
    .cut
    0.06
    _masks
    0.06
     boys
    0.06
     Modeling
    0.06
     getModel
    0.06
    ":[-
    0.06
    oped
    0.06
     bouquet
    0.06
    Act Density 0.005%

    No Known Activations