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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations used in formulas and equations

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

    Text within math environments (likely LaTeX)

    np_acts-logits-general · gemini-2.0-flash

    sequence of indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prnewswire
    -0.49
    kkende
    -0.49
     loài
    -0.48
    uhan
    -0.46
     Third
    -0.46
     calendriers
    -0.46
    Third
    -0.46
    原始内容存档于
    -0.45
    )]$
    -0.44
     ""],
    -0.44
    POSITIVE LOGITS
     next
    1.41
    next
    1.24
     Next
    1.16
    Next
    1.11
     nästa
    1.00
     NEXT
    1.00
    NEXT
    0.94
     previous
    0.93
    下一个
    0.89
     следующем
    0.89
    Act Density 0.439%

    No Known Activations