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

    Neuronpedia

    INDEX
    Explanations

    Code versions/configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .wh
    -0.07
    ↵↵
    -0.06
    λά
    -0.06
     qed
    -0.06
    围
    -0.06
    >Status
    -0.06
    ’an
    -0.06
    _particles
    -0.06
     Allah
    -0.06
    ْه
    -0.06
    POSITIVE LOGITS
     latter
    0.07
    ctors
    0.07
     dynamic
    0.06
     образ
    0.06
     составе
    0.06
    <Image
    0.06
    ntax
    0.06
     전체
    0.06
    ymbol
    0.06
     omit
    0.06
    Act Density 0.003%

    No Known Activations