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

    Neuronpedia

    INDEX
    Explanations

    finally, bus, ice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.95
    াম
    0.88
    να
    0.87
    odge
    0.82
    .
    0.81
    ترة
    0.79
     пытается
    0.78
    ساعد
    0.77
    йда
    0.77
    жет
    0.77
    POSITIVE LOGITS
    Nicht
    1.13
     Besonders
    1.08
    Jenis
    1.02
    Cult
    1.01
    Đi
    1.00
    Auch
    0.98
    መሳሳይ
    0.98
     MediaType
    0.97
     Zudem
    0.96
    Além
    0.95
    Act Density 0.001%

    No Known Activations