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

    Neuronpedia

    INDEX
    Explanations

    terms related to accusations and alerts regarding accidental actions

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

    starting with "acc" or "acety"

    np_acts-logits-general · gemini-2.0-flash

    words starting with acc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.78
    aarrggbb
    -0.77
    цездатний
    -0.75
    extAlignment
    -0.72
    !*\
    -0.72
    farer
    -0.71
    🏻
    -0.70
    脚注の使い方
    -0.69
     considérons
    -0.69
     متحده
    -0.68
    POSITIVE LOGITS
    cu
    0.54
    besch
    0.53
    aving
    0.50
     passés
    0.50
    reportWebVitals
    0.49
    Hard
    0.47
    ual
    0.46
    uate
    0.46
    änner
    0.46
     Hard
    0.46
    Act Density 0.673%

    No Known Activations