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

    Neuronpedia

    INDEX
    Explanations

    make good estimations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নিদ্র
    0.46
     नींद
    0.40
    ([])
    0.39
     trži
    0.39
    markt
    0.38
     দায়ী
    0.38
    mysqli
    0.38
     دهند
    0.37
    hitva
    0.37
    emberg
    0.37
    POSITIVE LOGITS
     sense
    0.59
     Sense
    0.56
     basic
    0.54
    sense
    0.53
    Sense
    0.52
    基本
    0.51
     estimations
    0.51
     calculations
    0.50
    基本的
    0.49
     sentido
    0.49
    Act Density 0.000%

    No Known Activations