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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    κας
    -0.07
    ็จพระ
    -0.07
    _hor
    -0.07
     executor
    -0.07
    ско
    -0.06
    arrera
    -0.06
     Bilim
    -0.06
    atrice
    -0.06
     similarities
    -0.06
     druhé
    -0.06
    POSITIVE LOGITS
     besteht
    0.07
     Spend
    0.07
     Bod
    0.07
    MASConstraintMaker
    0.07
    #endregion
    0.06
    _Copy
    0.06
    ={{↵
    0.06
     misleading
    0.06
    PathComponent
    0.06
    Began
    0.06
    Act Density 0.000%

    No Known Activations