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

    Neuronpedia

    INDEX
    Explanations

    peeled and cubed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mck
    0.50
    ёнок
    0.48
    েন্দ্রলাল
    0.47
    اں
    0.46
     समान
    0.46
    निष्ठ
    0.46
    َان
    0.46
    ítő
    0.45
    ದಲ್ಲಿ
    0.45
     জন্মদিন
    0.45
    POSITIVE LOGITS
    \
    0.58
     other
    0.56
     lakeside
    0.52
     y
    0.51
     as
    0.50
    \-
    0.50
     e
    0.49
     poolside
    0.48
     from
    0.48
    (
    0.47
    Act Density 0.008%

    No Known Activations