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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ্�
    -0.07
     Rad
    -0.06
    [++
    -0.06
    ็จ
    -0.06
    >()->
    -0.06
     humano
    -0.06
     Menschen
    -0.05
    BlockSize
    -0.05
     anger
    -0.05
    -modules
    -0.05
    POSITIVE LOGITS
    Screenshot
    0.07
     scams
    0.07
     infections
    0.06
    .cache
    0.06
    afone
    0.06
     транспорт
    0.06
    vection
    0.06
     oct
    0.06
     patch
    0.06
    不过
    0.06
    Act Density 0.072%

    No Known Activations