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

    Neuronpedia

    INDEX
    Explanations

    comparison of options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cour
    -0.07
     R
    -0.07
    iloc
    -0.06
    _req
    -0.06
    ़क
    -0.06
    our
    -0.06
    Suffix
    -0.06
    arg
    -0.06
    ่ย
    -0.06
    غة
    -0.06
    POSITIVE LOGITS
     subtly
    0.07
     Seite
    0.06
     сейчас
    0.06
    要
    0.06
     trí
    0.06
    cob
    0.06
    ίνει
    0.06
    (prompt
    0.06
     Comcast
    0.06
     seksi
    0.06
    Act Density 0.031%

    No Known Activations