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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     videot
    -0.07
    鲷
    -0.07
    浪漫
    -0.07
     zest
    -0.07
     autop
    -0.07
    ufact
    -0.07
     Airlines
    -0.07
    ourn
    -0.07
    .month
    -0.07
    constraint
    -0.07
    POSITIVE LOGITS
    !',↵
    0.08
     kaldı
    0.07
    :[
    0.07
    .tr
    0.07
    र
    0.07
    !!
    0.07
     ($("#
    0.06
     spark
    0.06
    0.06
    严厉打击
    0.06
    Act Density 0.000%

    No Known Activations