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

    Neuronpedia

    INDEX
    Explanations

    giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sonian
    -0.07
    atemala
    -0.07
    .box
    -0.06
    úsqueda
    -0.06
    _note
    -0.06
    /tag
    -0.06
    FromArray
    -0.06
     Babe
    -0.06
    racat
    -0.06
     yatır
    -0.06
    POSITIVE LOGITS
     dominate
    0.08
     column
    0.07
     manic
    0.07
    (Settings
    0.06
    ি�
    0.06
     sizable
    0.06
     neuro
    0.06
     CACHE
    0.06
    adaptive
    0.06
    를
    0.06
    Act Density 0.057%

    No Known Activations