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

    Neuronpedia

    INDEX
    Explanations

    programming syntax related to the structure and flow of code, particularly focusing on loops and control flow statements

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

    Characters appearing with "+" signs

    np_acts-logits-general · gemini-2.0-flash

    code snippet start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reaſon
    -0.76
    
    -0.75
     uſe
    -0.73
     poffible
    -0.68
     reſ
    -0.66
     cauſe
    -0.66
     reafon
    -0.66
     deſt
    -0.65
     preſent
    -0.64
     ſhould
    -0.64
    POSITIVE LOGITS
     Waray
    0.61
      (
    0.58
     Protobuf
    0.56
     actionTypes
    0.56
    ScopeManager
    0.55
     careers
    0.51
    TagHelper
    0.51
    BorderFactory
    0.50
    calipsis
    0.49
     doll
    0.49
    Act Density 0.026%

    No Known Activations