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

    Neuronpedia

    INDEX
    Explanations

    mutations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nf
    -0.06
     Ragnar
    -0.06
    wares
    -0.06
     Extraction
    -0.06
     compression
    -0.06
     discomfort
    -0.06
    าณาจ
    -0.06
     Gilbert
    -0.05
    高等
    -0.05
    -depend
    -0.05
    POSITIVE LOGITS
     Πέ
    0.07
     ‎
    0.06
     sublic
    0.06
     '''
    0.06
    =\"
    0.06
     relentlessly
    0.06
     AndAlso
    0.06
     ré
    0.06
    >>(↵
    0.06
    ='<
    0.06
    Act Density 0.003%

    No Known Activations