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

    Neuronpedia

    INDEX
    Explanations

    biological mechanisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Delete
    -0.07
    -payment
    -0.07
     holidays
    -0.07
    ��
    -0.07
     Trying
    -0.06
     giấy
    -0.06
    ảng
    -0.06
    charm
    -0.06
    ]↵↵↵
    -0.06
     ücretsiz
    -0.06
    POSITIVE LOGITS
     rer
    0.08
    _TW
    0.07
    .Sn
    0.06
    Sup
    0.06
    :NS
    0.06
    bnb
    0.06
     تصویر
    0.06
    _CS
    0.06
    931
    0.06
     Carroll
    0.06
    Act Density 0.039%

    No Known Activations