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

    Neuronpedia

    INDEX
    Explanations

    end tag or attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zelfde
    1.66
    :
    1.45
    ,
    1.44
    ー
    1.38
    )
    1.30
    pengaruhi
    1.28
    WallArray
    1.26
    наў
    1.25
    含ま
    1.23
    PrototypeOf
    1.23
    POSITIVE LOGITS
    s
    2.06
    ات
    1.80
    ς
    1.77
    oretically
    1.55
    T
    1.46
    B
    1.41
    ৫
    1.40
    S
    1.39
    ک
    1.36
    ก
    1.35
    Act Density 0.069%

    No Known Activations