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

    Neuronpedia

    INDEX
    Explanations

    8-bit, 16-bit, INT8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    වන
    0.49
    मीत
    0.46
    е
    0.45
    ve
    0.44
    udsman
    0.44
    ск
    0.41
    억원
    0.40
    ă
    0.40
    sey
    0.39
    side
    0.38
    POSITIVE LOGITS
     inconsc
    0.48
     invece
    0.48
     instead
    0.47
     incapable
    0.46
     reincarnation
    0.45
     Espí
    0.45
     sogenannte
    0.45
    REQUI
    0.45
     necrosis
    0.45
     실패
    0.44
    Act Density 0.016%

    No Known Activations