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

    Neuronpedia

    INDEX
    Explanations

    various mathematical formatting elements and structures, particularly in equations

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

    LaTeX environments and equations

    np_acts-logits-general · gemini-2.0-flash

    aligned mathematical environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cross
    -0.59
     --
    -0.55
    Cross
    -0.53
     Cross
    -0.52
    /**
    -0.52
    utilisons
    -0.51
    AutoScaleMode
    -0.50
    SourceChecksum
    -0.49
    VideoCapture
    -0.49
     –
    -0.48
    POSITIVE LOGITS
     Efq
    0.85
    )";
    0.84
     myſelf
    0.83
     Monfieur
    0.82
     $_"
    0.80
     ſeveral
    0.77
     auroit
    0.76
    GEBURTS
    0.73
     Theſe
    0.73
     ainfi
    0.73
    Act Density 0.116%

    No Known Activations