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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regardless
    -0.07
    ิตร
    -0.07
     Cary
    -0.06
     memset
    -0.06
     sar
    -0.06
     ld
    -0.06
     connector
    -0.06
     Zend
    -0.06
     Cheer
    -0.06
    важ
    -0.06
    POSITIVE LOGITS
    incip
    0.07
     기반
    0.07
    ีท
    0.07
     <?=$
    0.06
     Outcome
    0.06
    .Book
    0.06
     през
    0.06
    fox
    0.06
     зависимости
    0.06
    _adjust
    0.06
    Act Density 0.034%

    No Known Activations