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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LING
    -0.07
    ling
    -0.07
    축
    -0.06
    tif
    -0.06
     pisc
    -0.06
    inces
    -0.06
    appiness
    -0.06
    лению
    -0.06
    ajar
    -0.06
    -big
    -0.06
    POSITIVE LOGITS
    限制
    0.06
    ,,,
    0.06
     sitios
    0.06
    _vertex
    0.06
    роп
    0.06
     eapply
    0.06
    .GetKeyDown
    0.06
    andez
    0.06
    OWNER
    0.06
    extField
    0.06
    Act Density 0.248%

    No Known Activations