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

    Neuronpedia

    INDEX
    Explanations

    expressions related to mathematical functions and properties

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

    Mathematical or logical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and LaTeX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.51
     im
    -0.48
     
    -0.47
     hit
    -0.46
     d
    -0.44
     ban
    -0.43
     van
    -0.43
     Cor
    -0.43
     P
    -0.42
     St
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.93
     $=\
    0.88
     Normdatei
    0.82
    =\
    0.79
     pleaſure
    0.79
     houſe
    0.78
     myſelf
    0.76
     $=$
    0.75
     ſche
    0.75
    =<
    0.74
    Act Density 1.311%

    No Known Activations