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

    Neuronpedia

    INDEX
    Explanations

    something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pop
    -0.08
    =\"%
    -0.07
     conce
    -0.07
     focused
    -0.07
    _count
    -0.07
    fstream
    -0.06
     dominant
    -0.06
     FREE
    -0.06
    Occup
    -0.06
     fu
    -0.06
    POSITIVE LOGITS
     частина
    0.07
     Barrett
    0.07
     Wrestle
    0.06
    ρίζ
    0.06
    şam
    0.06
     things
    0.06
     требует
    0.06
     bakeka
    0.06
     significa
    0.06
     Мы
    0.05
    Act Density 0.030%

    No Known Activations