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

    Neuronpedia

    INDEX
    Explanations

    Leibniz, Nilakantha series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minor
    0.37
     foreman
    0.35
     Robert
    0.34
     cong
    0.34
     youths
    0.34
     Hebrew
    0.34
     మే
    0.34
    保守
    0.34
    माणे
    0.34
     critica
    0.34
    POSITIVE LOGITS
    谱
    0.41
    Nag
    0.39
    蒸
    0.39
     Gustaf
    0.38
    Agu
    0.38
    獣
    0.35
    Alc
    0.35
    adapter
    0.34
    Intersection
    0.34
     ಜೀವನ
    0.34
    Act Density 0.004%

    No Known Activations