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

    Neuronpedia

    INDEX
    Explanations

    say "omatic"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charset
    -0.07
    \\/
    -0.06
    _cn
    -0.06
    REFERENCE
    -0.06
    ционного
    -0.06
    γγελ
    -0.06
    /REC
    -0.06
     multimedia
    -0.06
    วง
    -0.06
    laması
    -0.06
    POSITIVE LOGITS
    بد
    0.06
     квад
    0.06
     又
    0.06
     WELL
    0.06
    'yi
    0.06
     гол
    0.06
     trespass
    0.06
     Dtype
    0.06
     कथ
    0.06
     Mark
    0.06
    Act Density 0.002%

    No Known Activations