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

    Neuronpedia

    INDEX
    Explanations

    vaginoplasty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informó
    0.42
     quadrad
    0.41
    及び
    0.41
    ii
    0.40
     ReLU
    0.40
    および
    0.39
    ²
    0.39
    zeption
    0.39
     iyo
    0.39
    kbeta
    0.39
    POSITIVE LOGITS
     winged
    0.39
     life
    0.38
     возвра
    0.38
     хочу
    0.38
     return
    0.38
    鬃
    0.38
    ﾛ
    0.37
    ро
    0.36
    的目标
    0.36
     overjoyed
    0.36
    Act Density 0.000%

    No Known Activations