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

    Neuronpedia

    INDEX
    Explanations

    neutral descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    1.58
    y
    1.33
    p
    1.26
    c
    1.24
    l
    1.23
    v
    1.16
    an
    1.15
    <0x0D>
    1.07
    x
    1.05
    kamer
    1.05
    POSITIVE LOGITS
     neutral
    1.48
     Neutral
    1.48
    Neutral
    1.40
    neutral
    1.32
    ла
    1.25
     нейтра
    1.23
    یک
    1.18
     neutrals
    1.12
     neutrality
    1.11
    ﮄ
    1.05
    Act Density 0.015%

    No Known Activations