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

    Neuronpedia

    INDEX
    Explanations

    find help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mengatasi
    0.80
    imethyl
    0.79
    }\!\
    0.79
     conectados
    0.79
     stator
    0.78
     wiad
    0.78
     nomad
    0.77
     situação
    0.77
     Knows
    0.77
    这种情况
    0.76
    POSITIVE LOGITS
    -"
    0.68
    xh
    0.66
     কাপ
    0.64
    тельством
    0.63
    DropDownItem
    0.62
     पुरस्कार
    0.61
    help
    0.60
    car
    0.60
    AR
    0.59
    ospital
    0.59
    Act Density 0.014%

    No Known Activations