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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otras
    -0.08
     Eduardo
    -0.07
    =context
    -0.07
     dazu
    -0.07
     masturbating
    -0.06
     último
    -0.06
     contra
    -0.06
     브라
    -0.06
     coorden
    -0.06
     diğer
    -0.06
    POSITIVE LOGITS
     filled
    0.10
     fill
    0.10
    -filled
    0.10
     filling
    0.09
     Fill
    0.09
    -fill
    0.08
    KF
    0.07
    Fill
    0.07
     fills
    0.07
    _Osc
    0.07
    Act Density 0.021%

    No Known Activations