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

    Neuronpedia

    INDEX
    Explanations

    indicative mood forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    owl
    0.76
     Camin
    0.75
    odoc
    0.74
     PSP
    0.71
     Tau
    0.71
     triun
    0.71
     Nim
    0.71
    Charm
    0.70
     USER
    0.68
     מס
    0.68
    POSITIVE LOGITS
     yaşında
    0.80
     ergän
    0.78
    𝕘
    0.73
    要知道
    0.73
    的時間
    0.72
    できるように
    0.70
    が大きい
    0.70
    maschine
    0.70
     minimizing
    0.69
    ができる
    0.69
    Act Density 0.001%

    No Known Activations