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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PS
    -0.07
     Crime
    -0.07
     putchar
    -0.06
    263
    -0.06
    UPS
    -0.06
    )//
    -0.06
    FileSystem
    -0.06
    ยาน
    -0.06
     Mou
    -0.06
     громадян
    -0.06
    POSITIVE LOGITS
    latex
    0.06
    .scroll
    0.06
    —you
    0.06
    (fields
    0.06
     між
    0.06
    esinin
    0.06
     โดย
    0.06
    "os
    0.06
     فيلم
    0.06
    _crossentropy
    0.06
    Act Density 0.000%

    No Known Activations