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

    Neuronpedia

    INDEX
    Explanations

    use with caution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zez
    0.50
    rn
    0.50
     protested
    0.48
    hma
    0.47
    ittees
    0.46
    orsese
    0.45
    ost
    0.44
    in
    0.44
    eni
    0.44
    uti
    0.44
    POSITIVE LOGITS
     Aplikasi
    0.47
     meneg
    0.46
     cualquier
    0.45
    أ
    0.44
     indeks
    0.43
     dapur
    0.43
     qualquer
    0.43
     persamaan
    0.43
     любой
    0.42
     sederhana
    0.41
    Act Density 0.000%

    No Known Activations