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

    Neuronpedia

    INDEX
    Explanations

    instances of comments or documentation sections in code

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

    * followed by click

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.67
    arangay
    -0.66
     dezelve
    -0.63
    kijken
    -0.61
     gesteld
    -0.60
     enfans
    -0.59
     pérd
    -0.58
     Perſ
    -0.58
    retudo
    -0.57
     Roskov
    -0.57
    POSITIVE LOGITS
    ↵
    0.42
    #
    0.42
    num
    0.40
    Num
    0.39
     *
    0.39
     Num
    0.38
     \\
    0.37
    multer
    0.37
     #
    0.37
    typeorm
    0.36
    Act Density 0.022%

    No Known Activations