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

    Neuronpedia

    INDEX
    Explanations

    IMDb numbers and IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UCKY
    0.45
    𒋛
    0.45
    ISO
    0.43
    iduciary
    0.42
    ORN
    0.41
    ঋ
    0.41
    canceled
    0.40
    ístico
    0.40
    Ꮳ
    0.40
    Station
    0.40
    POSITIVE LOGITS
     Literatura
    0.45
     (...)
    0.43
     正
    0.42
     Tel
    0.41
     नियम
    0.40
     Toast
    0.40
     Pener
    0.40
     [...]
    0.39
     July
    0.39
     Tip
    0.39
    Act Density 0.000%

    No Known Activations