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

    Neuronpedia

    INDEX
    Explanations

    it followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đc
    0.80
    usetzen
    0.71
    ziehungs
    0.71
    ട്ടുള്ള
    0.70
     tenéis
    0.69
    uzione
    0.69
    िएगा
    0.68
     लीजिएगा
    0.68
    渭
    0.67
     सका
    0.67
    POSITIVE LOGITS
     ,
    0.79
    ap
    0.74
    natural
    0.67
     ليش
    0.67
     Helps
    0.66
    ol
    0.65
    லத்தில்
    0.64
     confuses
    0.63
    ラク
    0.63
    el
    0.63
    Act Density 0.161%

    No Known Activations