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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    micro
    -0.06
    better
    -0.06
    作者
    -0.06
     التد
    -0.06
     undermining
    -0.06
    -org
    -0.06
    _GRA
    -0.06
    csrf
    -0.06
    stre
    -0.06
     Ö
    -0.06
    POSITIVE LOGITS
     flank
    0.09
     installment
    0.07
    employment
    0.07
     Seasons
    0.07
     Builders
    0.07
     Huff
    0.07
     festive
    0.07
    yl
    0.06
    花
    0.06
    keep
    0.06
    Act Density 0.004%

    No Known Activations