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

    Neuronpedia

    INDEX
    Explanations

    Deep Mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    距
    0.45
    obst
    0.42
    黍
    0.41
    NumConst
    0.39
    populations
    0.39
    istered
    0.38
    屐
    0.38
     correspond
    0.37
    তে
    0.37
    सेस
    0.37
    POSITIVE LOGITS
     deep
    0.99
     Deep
    0.92
    Deep
    0.88
    deep
    0.84
     глубо
    0.84
    深
    0.77
     깊
    0.74
     dive
    0.70
     Dive
    0.70
    深的
    0.70
    Act Density 0.015%

    No Known Activations