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

    Neuronpedia

    INDEX
    Explanations

    taking actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elements
    0.70
     territory
    0.66
     events
    0.65
     measure
    0.63
     matter
    0.63
     vengeance
    0.61
     thema
    0.60
     Billing
    0.59
     Events
    0.58
     wrong
    0.58
    POSITIVE LOGITS
     አስ
    0.82
    閁
    0.80
    IDOS
    0.80
    kates
    0.80
    étricas
    0.80
    busch
    0.80
     مشہور
    0.79
    ricos
    0.79
    írus
    0.79
    ளர்
    0.78
    Act Density 0.026%

    No Known Activations