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

    Neuronpedia

    INDEX
    Explanations

    customer service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esto
    0.44
    놓
    0.43
     lạ
    0.43
     haya
    0.43
    놨
    0.43
     hayan
    0.42
     alti
    0.42
    栢
    0.42
     rigu
    0.42
     ndani
    0.42
    POSITIVE LOGITS
     Accumulated
    0.44
    u
    0.41
    is
    0.41
    WL
    0.40
    j
    0.40
    武
    0.40
    Accum
    0.40
    ak
    0.39
    ̀nh
    0.39
    ્ય
    0.39
    Act Density 0.000%

    No Known Activations