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

    Neuronpedia

    INDEX
    Explanations

    instances of programming syntax or code-related terms

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

    list indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.71
    StoryboardSegue
    -0.64
    parsedMessage
    -0.62
    +#+#
    -0.61
    makeConstraints
    -0.59
    SBATCH
    -0.58
    󠁿
    -0.56
     betweenstory
    -0.56
     estekak
    -0.55
    -------------</
    -0.55
    POSITIVE LOGITS
     suspend
    0.33
     BitSet
    0.33
    Xna
    0.31
    Gre
    0.30
     collect
    0.29
     videoc
    0.29
     collecting
    0.28
     Gre
    0.28
     pare
    0.27
     children
    0.27
    Act Density 0.000%

    No Known Activations