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

    Neuronpedia

    INDEX
    Explanations

    Code and filenames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inmates
    -0.07
     lParam
    -0.06
    lack
    -0.06
     Sentry
    -0.06
    乡
    -0.06
     ud
    -0.06
     sürec
    -0.06
    tal
    -0.06
     HIM
    -0.06
     больше
    -0.06
    POSITIVE LOGITS
    Portable
    0.07
     Excellent
    0.07
     objedn
    0.06
    abh
    0.06
    _DECLS
    0.06
    phys
    0.06
    piel
    0.06
     دول
    0.06
    (fieldName
    0.06
    .os
    0.06
    Act Density 0.011%

    No Known Activations