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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the asterisk symbol, likely indicating special notes or comments in programming code

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

    dereferencing pointers/structs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inWeight
    -0.79
     propOrder
    -0.78
    majánló
    -0.76
     zwiſchen
    -0.76
     ་་
    -0.74
     müſſen
    -0.74
     ſind
    -0.73
     BoxDecoration
    -0.73
     queſta
    -0.72
     TextInputType
    -0.72
    POSITIVE LOGITS
    *
    0.72
     *
    0.43
    ...
    0.36
    --
    0.34
    Would
    0.33
     $
    0.33
     =
    0.33
    °
    0.33
     only
    0.32
    [
    0.32
    Act Density 0.008%

    No Known Activations