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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations related to transforms and functions

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

    LaTeX math delimiters

    np_acts-logits-general · gemini-2.0-flash

    math punctuation and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considérons
    -0.66
     gọn
    -0.58
    berfläche
    -0.54
    THISDAY
    -0.51
     isInitialized
    -0.51
    viesa
    -0.49
     gouvernements
    -0.49
     Référence
    -0.48
     mouseClicked
    -0.47
    STRUCTIONS
    -0.46
    POSITIVE LOGITS
     nakalista
    0.78
    aarrggbb
    0.69
    RegressionTest
    0.64
     snippetHide
    0.54
     Signalez
    0.53
    ########.
    0.53
    adaptiveStyles
    0.53
    twimg
    0.52
    >.</
    0.52
    
    0.51
    Act Density 1.239%

    No Known Activations