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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fo
    -0.07
    CR
    -0.06
    (ff
    -0.06
    يك
    -0.06
     ✔
    -0.06
    (rec
    -0.06
    凉
    -0.06
     skys
    -0.06
     krb
    -0.06
     Cro
    -0.06
    POSITIVE LOGITS
    -sort
    0.07
     revival
    0.06
     )(
    0.06
    _passwd
    0.06
     phrases
    0.06
     Death
    0.06
    _tip
    0.06
    -educated
    0.06
     edition
    0.05
    -window
    0.05
    Act Density 0.064%

    No Known Activations