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

    Neuronpedia

    INDEX
    Explanations

    variety and specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amsmath
    0.50
    ing
    0.49
    altura
    0.48
    rung
    0.48
    っている
    0.46
    arat
    0.45
    going
    0.45
    ंनी
    0.45
    ायचे
    0.44
    talent
    0.44
    POSITIVE LOGITS
     nella
    0.52
     ″
    0.49
     bagno
    0.48
     personaggi
    0.47
     Saddam
    0.46
    httphttps
    0.46
     con
    0.45
     fuori
    0.44
     ಭ
    0.44
     ی
    0.44
    Act Density 0.002%

    No Known Activations