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

    Neuronpedia

    INDEX
    Explanations

    vibe check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.53
    :
    0.51
     three
    0.46
     "
    0.45
     (
    0.44
     aforementioned
    0.39
    4
    0.39
     two
    0.39
     at
    0.38
     crux
    0.38
    POSITIVE LOGITS
    ॕ
    0.35
    ্্র
    0.34
    ຂໍ້ມ
    0.33
    DeathRecord
    0.33
    也能
    0.32
    uları
    0.32
    cpuCycle
    0.32
    DanhMucSP
    0.32
    vykor
    0.31
     costruire
    0.31
    Act Density 0.218%

    No Known Activations