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

    Neuronpedia

    INDEX
    Explanations

    stack overflow questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hindu
    -0.07
     puta
    -0.07
     받아
    -0.07
     took
    -0.07
    \Catalog
    -0.06
     astonishing
    -0.06
    丝
    -0.06
     fibonacci
    -0.06
    spawn
    -0.06
     ks
    -0.06
    POSITIVE LOGITS
     CLI
    0.06
    igt
    0.06
    /meta
    0.06
    _meas
    0.06
     پي
    0.06
     pubb
    0.06
    א
    0.06
     HG
    0.06
     إذ
    0.06
    ONGLONG
    0.06
    Act Density 0.112%

    No Known Activations