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

    Neuronpedia

    INDEX
    Explanations

    Drop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ینه
    -0.07
    دم
    -0.07
    组
    -0.06
    _Info
    -0.06
    د
    -0.06
    ABCDE
    -0.06
    rf
    -0.06
    CUSTOM
    -0.06
    雅黑
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Neal
    0.07
    .New
    0.06
     金
    0.06
     Crowley
    0.06
     dém
    0.06
     інтер
    0.06
     ウ
    0.06
    บาย
    0.06
     tisk
    0.06
     لی
    0.06
    Act Density 0.012%

    No Known Activations