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

    Neuronpedia

    INDEX
    Explanations

    utility imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.65
     I
    0.58
    ،
    0.54
    ।
    0.53
    Sales
    0.53
    F
    0.52
     Supervision
    0.51
    Player
    0.49
     Player
    0.48
    routes
    0.48
    POSITIVE LOGITS
     utility
    0.54
     utilities
    0.52
     util
    0.50
    .
    0.49
    ][:
    0.48
     Ut
    0.48
     dire
    0.48
     diperlukan
    0.47
    म्बर
    0.47
     trợ
    0.47
    Act Density 0.008%

    No Known Activations