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

    Neuronpedia

    INDEX
    Explanations

    specific statements for corrections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sonor
    0.51
    סה
    0.48
    ാവ്
    0.47
    Energ
    0.45
     віднов
    0.45
     DIR
    0.45
    гія
    0.45
     cub
    0.44
     sonore
    0.43
    //$
    0.42
    POSITIVE LOGITS
    ui
    0.48
    an
    0.48
    ulated
    0.48
    ivant
    0.43
     मनात
    0.42
    stam
    0.41
     இடம்பெ
    0.41
    eid
    0.41
     repente
    0.40
    uid
    0.40
    Act Density 0.002%

    No Known Activations