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

    Neuronpedia

    INDEX
    Explanations

    assignment operators and function declarations in code snippets

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.58
     itſelf
    -0.56
    Gön
    -0.55
    balleur
    -0.55
    crí
    -0.53
    tonode
    -0.52
     plufieurs
    -0.52
     myſelf
    -0.51
     ſch
    -0.48
     <=",
    -0.47
    POSITIVE LOGITS
    iomanip
    0.41
    SuppressLint
    0.39
     Impossible
    0.39
    sizeof
    0.37
    ISupport
    0.37
    GIVEREF
    0.37
    UseVisualStyle
    0.36
     Bob
    0.36
    NullCheck
    0.36
    unistd
    0.35
    Act Density 0.006%

    No Known Activations