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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nghĩ
    -0.06
    porno
    -0.06
    阳城
    -0.06
    outers
    -0.06
     byla
    -0.06
    mıştı
    -0.06
    .now
    -0.06
    .span
    -0.06
     boil
    -0.06
    Known
    -0.06
    POSITIVE LOGITS
    研究所
    0.06
    ®,
    0.06
    (Application
    0.06
    AO
    0.06
    .BorderStyle
    0.06
     (),
    0.06
    如下
    0.06
     případě
    0.06
     než
    0.06
    <f
    0.06
    Act Density 0.069%

    No Known Activations