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

    Neuronpedia

    INDEX
    Explanations

    programming constructs, particularly loops and conditional statements

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

    Mathematical or programming notation

    np_acts-logits-general · gemini-2.0-flash

    identifiers or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    if
    -0.56
     
    -0.56
     or
    -0.48
    /
    -0.48
    ↵↵
    -0.48
     “
    -0.48
    tvguidetime
    -0.48
    less
    -0.47
     "
    -0.47
    ↵
    -0.45
    POSITIVE LOGITS
    VersionUID
    0.93
    AsUp
    0.86
    djangoproject
    0.85
    Cartney
    0.82
    kloped
    0.82
    SBATCH
    0.80
    nemia
    0.79
     pylint
    0.79
    rizona
    0.77
     GIPHY
    0.76
    Act Density 0.253%

    No Known Activations