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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <System
    -0.07
     تحقیق
    -0.06
    -operator
    -0.06
     Coff
    -0.06
    .monitor
    -0.06
     rop
    -0.06
     bilingual
    -0.06
     propaganda
    -0.06
     Adjust
    -0.06
    unities
    -0.06
    POSITIVE LOGITS
    怎
    0.07
    NotBlank
    0.07
    啦
    0.06
    _TOO
    0.06
    enade
    0.06
    صل
    0.06
    하세요
    0.06
     ẩn
    0.06
    ู่
    0.06
    ARIANT
    0.06
    Act Density 0.002%

    No Known Activations