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

    Neuronpedia

    INDEX
    Explanations

    principal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,Th
    -0.07
     Mak
    -0.07
     yetiş
    -0.07
     alleges
    -0.07
     выдел
    -0.06
     Monk
    -0.06
    .InnerText
    -0.06
    .Highlight
    -0.06
     eligible
    -0.06
     Tutorial
    -0.06
    POSITIVE LOGITS
    od
    0.07
     shortcode
    0.06
     sở
    0.06
     사람
    0.06
     (!
    0.06
    /apt
    0.06
    FromNib
    0.06
     torque
    0.06
    оск
    0.06
     싱글
    0.06
    Act Density 0.005%

    No Known Activations