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

    Neuronpedia

    INDEX
    Explanations

    IL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effectiveness
    -0.07
    _specific
    -0.06
    rgan
    -0.06
    .source
    -0.06
    'y
    -0.06
    _mar
    -0.06
     institutes
    -0.06
     inclu
    -0.06
     deficiencies
    -0.06
    anagan
    -0.06
    POSITIVE LOGITS
    il
    0.07
    .").
    0.07
    Calibri
    0.06
    IL
    0.06
    .:.:
    0.06
    AL
    0.06
    .relu
    0.06
     skuteč
    0.06
    ild
    0.06
    	On
    0.06
    Act Density 0.006%

    No Known Activations