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

    Neuronpedia

    INDEX
    Explanations

    government recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rom
    -0.07
    社会化
    -0.07
     protest
    -0.07
    צל
    -0.06
    ���
    -0.06
    Crypt
    -0.06
    سعد
    -0.06
     sanctioned
    -0.06
     incarcerated
    -0.06
     professionally
    -0.06
    POSITIVE LOGITS
    咽喉
    0.08
    豪宅
    0.07
     EventBus
    0.07
    تلفزي
    0.07
    ('{{
    0.07
     attent
    0.07
    笋
    0.07
    $data
    0.07
    (('
    0.07
    ]}>↵
    0.07
    Act Density 0.067%

    No Known Activations