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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Encyclopedia
    0.85
    Here
    0.83
    <strong>
    0.80
    ynyt
    0.79
    britann
    0.77
    <h3>
    0.75
    Berikut
    0.75
     തന്നെയാണ്
    0.73
     Exact
    0.73
    Deaths
    0.72
    POSITIVE LOGITS
     ulo
    0.72
     tipo
    0.69
     electro
    0.69
     قی
    0.69
     club
    0.66
     этом
    0.66
     puncture
    0.66
    ᇁ
    0.66
    卩
    0.66
     شكل
    0.65
    Act Density 0.099%

    No Known Activations