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

    Neuronpedia

    INDEX
    Explanations

    LaTeX and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    writing
    -0.07
     petitioner
    -0.07
     insistence
    -0.06
    God
    -0.06
     SIGN
    -0.06
     expanded
    -0.06
     God
    -0.06
    ed
    -0.06
     midpoint
    -0.06
     ign
    -0.06
    POSITIVE LOGITS
    EIF
    0.07
    €
    0.07
    _TODO
    0.07
    تری
    0.07
     stejně
    0.07
    हम
    0.07
    =n
    0.06
    inke
    0.06
    erli
    0.06
     Starter
    0.06
    Act Density 0.000%

    No Known Activations