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

    Neuronpedia

    INDEX
    Explanations

    script and function definitions in programming-related text

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

    `.` followed by `decode` in code

    np_acts-logits-general · gemini-2.0-flash

    decode, next field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.73
     snippetHide
    -0.61
    SharedDtor
    -0.60
    StoryboardSegue
    -0.59
     GetEnumerator
    -0.59
     defStyle
    -0.58
    цездатний
    -0.57
    featureID
    -0.55
     oprot
    -0.53
     HttpHeaders
    -0.53
    POSITIVE LOGITS
     next
    0.70
    continue
    0.63
     continuing
    0.63
     continue
    0.62
    next
    0.59
     CONTINUE
    0.58
     till
    0.55
     continues
    0.55
    继续
    0.54
    continues
    0.54
    Act Density 0.463%

    No Known Activations