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

    Neuronpedia

    INDEX
    Explanations

    initiating an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を示す
    0.62
    appears
    0.62
    рім
    0.60
     új
    0.57
    appearing
    0.57
    पूर्वक
    0.57
    small
    0.57
    statusCode
    0.57
     pequeños
    0.56
    ụ
    0.56
    POSITIVE LOGITS
     MSI
    0.71
    不想
    0.67
     worried
    0.67
     dread
    0.67
     اصلا
    0.66
     obsessed
    0.64
     Unity
    0.64
     inició
    0.63
     invested
    0.63
     want
    0.62
    Act Density 0.003%

    No Known Activations