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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate potential outcomes or uncertainties

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

    modal verbs and "go"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.35
     Rakyat
    -0.30
    签
    -0.30
     cuno
    -0.27
    paravant
    -0.27
    warzys
    -0.26
    couvrez
    -0.26
     заключа
    -0.25
    ویس
    -0.25
    Personendaten
    -0.24
    POSITIVE LOGITS
     myſelf
    0.69
     ſta
    0.65
     autorytatywna
    0.65
    oa̍t
    0.65
    aarrggbb
    0.63
    躇
    0.61
     Anſ
    0.61
     للاسماء
    0.60
     AssemblyTitle
    0.59
     الحره
    0.59
    Act Density 0.406%

    No Known Activations