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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to algorithms or data structures

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    String parsing and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.56
     familiale
    -0.44
    #+#
    -0.41
    impresa
    -0.39
    interprétation
    -0.39
     kobiety
    -0.38
     szkoły
    -0.38
    -0.38
     lección
    -0.38
    IUrlHelper
    -0.36
    POSITIVE LOGITS
    FunctionFlags
    0.46
     strategy
    0.45
    ItemBackground
    0.44
     interval
    0.43
    bun
    0.43
     manipula
    0.43
    Meik
    0.42
    Sof
    0.42
     secu
    0.41
    üttel
    0.41
    Act Density 0.554%

    No Known Activations