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

    Neuronpedia

    INDEX
    Explanations

    how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چنان
    0.66
    েস
    0.65
    ו
    0.64
     तौर
    0.63
     colet
    0.60
    其他
    0.59
    ircle
    0.59
     Nahi
    0.58
    ર
    0.58
    ν
    0.57
    POSITIVE LOGITS
     государства
    0.65
    ्य
    0.65
    sic
    0.64
    ſ
    0.62
    ArrayAdapter
    0.60
    াল
    0.60
    NYSE
    0.59
    ธ์
    0.59
    檛
    0.59
    PRESSED
    0.58
    Act Density 0.105%

    No Known Activations