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

    Neuronpedia

    INDEX
    Explanations

    I will get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Browse
    0.74
     binder
    0.71
    *****",
    0.67
     embracing
    0.66
    Э
    0.65
    Основные
    0.64
    вич
    0.64
     binders
    0.64
    Hopefully
    0.63
    ARE
    0.63
    POSITIVE LOGITS
    کٹ
    0.74
    𝑓
    0.72
    setShow
    0.68
    ۍ
    0.65
    ressed
    0.65
     şey
    0.64
    f
    0.63
    ف
    0.62
    𝚏
    0.62
    ería
    0.61
    Act Density 0.010%

    No Known Activations