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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     di
    0.50
    aldi
    0.49
    EN
    0.46
    _
    0.45
     chương
    0.45
    di
    0.45
    is
    0.44
     pallet
    0.42
     delicious
    0.42
     medications
    0.41
    POSITIVE LOGITS
    ęć
    0.48
    FUNCION
    0.48
    ณะ
    0.46
     लाने
    0.45
    ον
    0.45
     बताएं
    0.45
    ModeBanner
    0.45
    𝘽
    0.45
    ้า
    0.44
    кура
    0.44
    Act Density 0.001%

    No Known Activations