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

    Neuronpedia

    INDEX
    Explanations

    could you tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ोगे
    0.73
     interpolate
    0.72
    マンス
    0.71
     प्रीम
    0.68
    गराज
    0.67
     rescaling
    0.66
    romad
    0.66
     Sadie
    0.64
     prismatic
    0.64
    Articulation
    0.64
    POSITIVE LOGITS
     could
    0.68
     ਚ
    0.64
    იტ
    0.59
    could
    0.56
     deceived
    0.56
     گذر
    0.54
    までも
    0.54
     COULD
    0.52
     driven
    0.52
    鬼
    0.51
    Act Density 0.196%

    No Known Activations