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

    Neuronpedia

    INDEX
    Explanations

    proactively telling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tg
    0.38
     Rada
    0.37
     innovating
    0.36
    čných
    0.35
    ൾ
    0.35
    ThreadPool
    0.35
     Tik
    0.35
    Analyzing
    0.35
     Elon
    0.34
    ളെ
    0.34
    POSITIVE LOGITS
     சிறப்பாக
    0.44
    সুল
    0.43
     slider
    0.41
    غان
    0.40
    pav
    0.39
     окт
    0.39
    sliders
    0.39
     sliders
    0.39
    सूर्
    0.39
     Butcher
    0.38
    Act Density 0.003%

    No Known Activations