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

    Neuronpedia

    INDEX
    Explanations

    code snippets and syntax elements in programming language contexts

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

    Code, math symbols, or uncommon characters

    np_acts-logits-general · gemini-2.0-flash

    technical terms and string manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readObject
    -0.54
     notare
    -0.47
     وسلم
    -0.46
     corpi
    -0.46
    dost
    -0.46
    Globals
    -0.43
     excepted
    -0.43
     intitulé
    -0.43
    typedef
    -0.42
     तो
    -0.42
    POSITIVE LOGITS
    <?
    0.68
    ">//
    0.63
    saraba
    0.62
    #
    0.62
    fjspx
    0.60
     unknownFields
    0.57
     GoogleFonts
    0.57
    verwijspagina
    0.57
     ujednoznacz
    0.56
     Agencia
    0.55
    Act Density 0.190%

    No Known Activations