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

    Neuronpedia

    INDEX
    Explanations

    .microsoft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Currently
    -0.07
     Coat
    -0.07
    Concat
    -0.06
     Anchor
    -0.06
     Any
    -0.06
    _tag
    -0.06
    peated
    -0.06
    難
    -0.06
     currently
    -0.06
    /train
    -0.06
    POSITIVE LOGITS
    InnerText
    0.07
    πος
    0.07
    INATION
    0.06
     pursuing
    0.06
    Studio
    0.06
    prise
    0.06
    슬
    0.06
     росій
    0.06
    égorie
    0.06
    інь
    0.06
    Act Density 0.001%

    No Known Activations