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

    Neuronpedia

    INDEX
    Explanations

    Executive compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egr
    -0.07
    -points
    -0.07
     Cox
    -0.07
     جن
    -0.07
     susceptibility
    -0.06
     modest
    -0.06
     impatient
    -0.06
     Pig
    -0.06
     valu
    -0.06
    modity
    -0.06
    POSITIVE LOGITS
    couz
    0.06
    brains
    0.06
     Населення
    0.06
    _CH
    0.06
    кав
    0.06
    Runtime
    0.06
     pré
    0.06
     мус
    0.06
     syll
    0.05
    .Person
    0.05
    Act Density 0.010%

    No Known Activations