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

    Neuronpedia

    INDEX
    Explanations

    query parameters and data filtering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erset
    0.81
    rock
    0.79
    Stone
    0.78
    ൃശ
    0.76
    石頭
    0.76
    OSH
    0.76
    ेक
    0.75
    deleteAll
    0.75
    ర
    0.74
    pertension
    0.74
    POSITIVE LOGITS
    CLUDING
    0.72
     robes
    0.71
     partecipanti
    0.68
     feud
    0.67
     nobis
    0.67
    0.66
     පිළිබඳ
    0.66
    ības
    0.65
    섭
    0.65
    ডেট
    0.65
    Act Density 0.004%

    No Known Activations