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

    Neuronpedia

    INDEX
    Explanations

    generally preferred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paso
    0.47
     bức
    0.43
     palpit
    0.42
     impec
    0.41
     bureaucratic
    0.41
     expir
    0.41
     eager
    0.41
     regel
    0.41
    exp
    0.40
     burning
    0.40
    POSITIVE LOGITS
    Thoreau
    0.46
    8
    0.45
     கிரே
    0.45
     সাহায
    0.42
    Bat
    0.42
    Fancy
    0.40
    Rit
    0.39
    噸
    0.39
     компью
    0.39
    griffen
    0.38
    Act Density 0.053%

    No Known Activations