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

    Neuronpedia

    INDEX
    Explanations

    manual and scientific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.58
    Scripts
    0.57
    。[
    0.57
    सि
    0.56
    caso
    0.51
    ாது
    0.50
    calling
    0.50
    ও
    0.50
    Created
    0.49
    Ore
    0.49
    POSITIVE LOGITS
     defesa
    0.68
    yna
    0.64
    t
    0.64
    િ
    0.64
     hydroxide
    0.64
     difesa
    0.62
     função
    0.61
     rendre
    0.61
     CARD
    0.61
     coût
    0.61
    Act Density 0.000%

    No Known Activations