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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     economics
    -0.07
     UPC
    -0.06
     Taiwanese
    -0.06
    angs
    -0.06
    艺术
    -0.06
     LE
    -0.06
     ấm
    -0.06
     overl
    -0.06
     elem
    -0.06
    _SH
    -0.06
    POSITIVE LOGITS
    ství
    0.07
     организа
    0.06
    .recycle
    0.06
    ость
    0.06
    orElse
    0.06
    brıs
    0.06
     italiani
    0.06
    ('../../
    0.06
     Rhe
    0.06
     đị
    0.06
    Act Density 0.082%

    No Known Activations