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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters indicating immediacy or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    in other words, namely, equivalently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.49
     deleteUser
    -0.44
    reonine
    -0.43
    idopsis
    -0.41
    ertal
    -0.41
    lour
    -0.39
    Working
    -0.38
    løs
    -0.38
     \%
    -0.37
     invers
    -0.37
    POSITIVE LOGITS
    即
    1.91
     即
    1.56
    즉
    0.96
    卽
    0.94
    即是
    0.92
     tức
    0.86
    既
    0.85
    곧
    0.71
     cioè
    0.70
     Namely
    0.67
    Act Density 0.001%

    No Known Activations