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

    Neuronpedia

    INDEX
    Explanations

    security and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    woman
    0.69
    idia
    0.68
    Daily
    0.68
     seca
    0.67
    বেল
    0.66
    Contacto
    0.66
    Culture
    0.66
     движение
    0.66
    DEM
    0.66
    meth
    0.66
    POSITIVE LOGITS
     pesky
    1.02
     terrifying
    0.86
     importanti
    0.86
     safely
    0.83
     নিরাপ
    0.81
     safer
    0.81
     tricky
    0.79
     notoriously
    0.78
    ដ៏
    0.76
     horrors
    0.75
    Act Density 1.981%

    No Known Activations