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

    Neuronpedia

    INDEX
    Explanations

    references to programming constructs and their functionalities in a documentation context

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

    Java Doc, technical English, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.40
    主
    -0.39
     
    -0.39
    _
    -0.38
    1
    -0.37
     Schra
    -0.36
     credit
    -0.36
    2
    -0.36
    ud
    -0.35
    3
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.83
     queſta
    0.82
    ロウィン
    0.81
    0.75
     $_(
    0.75
    Geplaatst
    0.75
    parsedMessage
    0.73
     $_"
    0.73
     témoig
    0.72
    httphttps
    0.71
    Act Density 0.005%

    No Known Activations