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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wrath
    -0.08
    _free
    -0.07
    .Uint
    -0.06
    ुझ
    -0.06
    ASF
    -0.06
     olacaktır
    -0.06
    leftrightarrow
    -0.06
     widow
    -0.06
    .warning
    -0.06
    .with
    -0.06
    POSITIVE LOGITS
    体育
    0.06
    PKG
    0.06
     hp
    0.06
    iration
    0.06
    discover
    0.06
     motions
    0.06
    ltk
    0.06
    -avatar
    0.06
     прик
    0.06
    .Media
    0.06
    Act Density 0.031%

    No Known Activations