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

    Neuronpedia

    INDEX
    Explanations

    public, counter, Packard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    1.13
    надца
    1.10
    りの
    1.07
    zelfde
    1.04
    ки
    1.03
    n
    1.02
    ל
    1.02
    ad
    1.01
    ot
    1.01
    setScale
    1.01
    POSITIVE LOGITS
     and
    1.11
    )،
    0.99
    AndUpdate
    0.98
    |)
    0.96
    أ
    0.96
    𝗰
    0.95
    𝘀
    0.94
     Todo
    0.93
    }|
    0.92
    )
    0.91
    Act Density 0.000%

    No Known Activations