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

    Neuronpedia

    INDEX
    Explanations

    references to issues or problem statements in a technical context

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

    issue # references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.46
     Waray
    -0.46
    Tikang
    -0.45
    tagHelperRunner
    -0.45
    onActivityResult
    -0.43
     الرياضيه
    -0.43
    SourceChecksum
    -0.41
    TagMode
    -0.41
    jspx
    -0.39
    ChildScrollView
    -0.39
    POSITIVE LOGITS
    Vidite
    0.47
     <<<<<<<<<<<<<<
    0.43
    
    0.42
     fubject
    0.41
     thermique
    0.40
    welijk
    0.40
    CAPITAL
    0.40
     lenker
    0.40
     internally
    0.39
     Handbuch
    0.39
    Act Density 0.012%

    No Known Activations