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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Suppress
    -0.07
     honda
    -0.07
    -around
    -0.07
    (IS
    -0.07
    _leader
    -0.07
    isco
    -0.06
     Corner
    -0.06
     seminars
    -0.06
     fame
    -0.06
     Operator
    -0.06
    POSITIVE LOGITS
    ьогодні
    0.07
    휴
    0.07
    是什么
    0.07
     eauto
    0.07
     आपक
    0.07
    ично
    0.06
     Helpful
    0.06
    어서
    0.06
    ünü
    0.06
    livě
    0.06
    Act Density 0.006%

    No Known Activations