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

    Neuronpedia

    INDEX
    Explanations

    threat intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    1.31
    z
    1.04
     uncl
    0.88
    д
    0.86
    us
    0.84
    maar
    0.82
    <0xA0>
    0.82
    itati
    0.81
    ത്
    0.80
    ش
    0.80
    POSITIVE LOGITS
    𝐨
    1.28
    𝐠
    1.25
    𝐧
    1.24
    𝐚
    1.17
    𝐞
    1.16
    chainId
    1.15
    𝐭
    1.13
    :],
    1.12
    𝐜
    1.07
    𝟐
    1.05
    Act Density 0.000%

    No Known Activations