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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    porno
    -0.06
     tavsiye
    -0.06
    ázd
    -0.06
    เดอร
    -0.06
    ?<
    -0.06
    ’ye
    -0.06
     lorem
    -0.06
     Deer
    -0.06
     Пав
    -0.06
    biased
    -0.06
    POSITIVE LOGITS
    atisfied
    0.07
     Anyone
    0.06
    unicipio
    0.06
     Antony
    0.06
    αιν
    0.06
    理
    0.06
    PlainOldData
    0.06
    \Controller
    0.06
     Unexpected
    0.06
     نص
    0.06
    Act Density 0.001%

    No Known Activations