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

    Neuronpedia

    INDEX
    Explanations

    commands or expressions of intention

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

    expressing desired actions or intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     старости
    -0.36
     "@/
    -0.35
     butterknife
    -0.33
    ⊱
    -0.32
     Maxi
    -0.32
    をお願い
    -0.32
    llac
    -0.32
    labelledby
    -0.32
    textra
    -0.31
     Ripper
    -0.31
    POSITIVE LOGITS
     numberOfRows
    0.55
    CloseOperation
    0.52
    endphp
    0.52
    vician
    0.51
     وتسجيلات
    0.50
     Geduld
    0.50
    verifyException
    0.50
    setVerticalGroup
    0.50
    сылкі
    0.50
     Türen
    0.50
    Act Density 0.015%

    No Known Activations