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

    Neuronpedia

    INDEX
    Explanations

    in English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inki
    0.79
     यूरोपीय
    0.78
     źród
    0.76
    Prés
    0.74
     Được
    0.74
     හොඳ
    0.73
     Çocuk
    0.72
    Tabla
    0.72
     اچھی
    0.71
    सर्व
    0.70
    POSITIVE LOGITS
     view
    0.75
     View
    0.73
     woe
    0.70
     hygiene
    0.69
     crossed
    0.68
     crossing
    0.66
     uptake
    0.66
    ifference
    0.66
     heaven
    0.66
     imagination
    0.65
    Act Density 0.010%

    No Known Activations