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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

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

    Python code blocks and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.69
     zijne
    -0.60
     ſind
    -0.60
    tagHelperRunner
    -0.57
     Grüße
    -0.55
    Nachteile
    -0.54
     desmotivaciones
    -0.54
     emailAlready
    -0.53
    Hauptartikel
    -0.53
     $_(
    -0.52
    POSITIVE LOGITS
    NamedQueries
    0.51
     "..\..\..\
    0.39
     compte
    0.38
    Réalisation
    0.34
     John
    0.32
     "..\..\
    0.32
    AutoScaleMode
    0.32
     frequency
    0.31
     account
    0.31
    delwed
    0.31
    Act Density 0.016%

    No Known Activations