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

    Neuronpedia

    INDEX
    Explanations

    apply to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    selves
    1.28
    ții
    1.10
    辆
    1.09
    fichier
    1.07
    客様
    1.04
    هُ
    1.02
     poissons
    1.01
     kilometers
    1.01
     artefacts
    1.00
     winding
    0.99
    POSITIVE LOGITS
    ឬ
    1.25
    𝒕
    1.22
     всего
    1.17
    tt
    1.15
    ttl
    1.10
     Chỉ
    1.08
     abge
    1.07
    tta
    1.06
    t
    1.05
    ting
    1.04
    Act Density 0.000%

    No Known Activations