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

    Neuronpedia

    INDEX
    Explanations

    lining up/being out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filetype
    -0.07
    Sat
    -0.07
    そ
    -0.06
    مین
    -0.06
     programmer
    -0.06
    82
    -0.06
    oid
    -0.06
     black
    -0.06
     Ara
    -0.06
    ok
    -0.06
    POSITIVE LOGITS
    bě
    0.06
    ếp
    0.06
     delight
    0.06
    能够
    0.06
     pulmonary
    0.06
    ancia
    0.06
    Islamic
    0.06
     Совет
    0.06
     triang
    0.06
    :]
    0.06
    Act Density 0.009%

    No Known Activations