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

    Neuronpedia

    INDEX
    Explanations

    actions or events that involve submission, execution, or processing in various contexts

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

    actions being completed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.77
    Predecesor
    -0.75
     Chwiliwch
    -0.73
     الرياضيه
    -0.66
    Personendaten
    -0.65
     betweenstory
    -0.63
    urlopen
    -0.63
     gynhyrchwyd
    -0.62
     HasFactory
    -0.60
    contentLoaded
    -0.59
    POSITIVE LOGITS
     stuff
    0.42
     gets
    0.41
     getting
    0.40
     gonna
    0.40
    get
    0.39
     gettin
    0.38
    getting
    0.36
     somebody
    0.36
     wanna
    0.35
     get
    0.35
    Act Density 0.026%

    No Known Activations