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

    Neuronpedia

    INDEX
    Explanations

    model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     غور
    0.71
     मॉल
    0.70
     जिनके
    0.68
     سماعت
    0.65
    ethylsulfanyl
    0.64
     હાથ
    0.63
     leggings
    0.62
    करणा
    0.62
     becom
    0.61
    弋
    0.61
    POSITIVE LOGITS
    ♩
    0.65
     parada
    0.65
    agues
    0.62
    쾌
    0.62
    :</
    0.62
    artoum
    0.62
     пара
    0.62
    »),
    0.61
     pá
    0.61
     गुप्त
    0.59
    Act Density 0.098%

    No Known Activations