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

    Neuronpedia

    INDEX
    Explanations

    categorizing people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enabled
    -0.06
    /twitter
    -0.06
     เป
    -0.06
     tisíc
    -0.06
    новаж
    -0.06
    чного
    -0.06
    цит
    -0.06
     erased
    -0.06
     pursuant
    -0.06
     أخرى
    -0.06
    POSITIVE LOGITS
    나요
    0.07
    autos
    0.06
    ;';↵
    0.06
     queued
    0.06
    .offset
    0.06
    atitis
    0.06
    enga
    0.06
    ey
    0.06
     atmos
    0.06
    _io
    0.06
    Act Density 0.014%

    No Known Activations