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

    Neuronpedia

    INDEX
    Explanations

    significant identifiers or keywords related to structure and organization

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

    first value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хать
    -0.36
     recor
    -0.32
     dAtA
    -0.31
    luiting
    -0.30
    zeln
    -0.30
     від
    -0.28
    録
    -0.28
     fun
    -0.27
    投
    -0.27
    收
    -0.26
    POSITIVE LOGITS
    canActivate
    0.93
     '\\;'
    0.58
     ſta
    0.55
     Perſ
    0.55
    StoryboardSegue
    0.54
    IndentedString
    0.54
     purpoſe
    0.54
     Eſ
    0.53
    jsonwebtoken
    0.53
     EconPapers
    0.53
    Act Density 0.001%

    No Known Activations