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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pdo
    -0.07
    Location
    -0.07
     Casting
    -0.07
    Bal
    -0.07
    وج
    -0.06
    '})
    -0.06
    ntag
    -0.06
    .Cho
    -0.06
    �
    -0.06
    carbon
    -0.06
    POSITIVE LOGITS
    语
    0.07
    .Flags
    0.07
     offseason
    0.07
    (VALUE
    0.06
    _Valid
    0.06
     使用
    0.06
    =create
    0.06
     submodule
    0.06
    .reject
    0.06
     runApp
    0.06
    Act Density 0.000%

    No Known Activations