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

    Neuronpedia

    INDEX
    Explanations

    LaTeX and Scheme code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ně
    0.38
    NaOH
    0.38
    ashire
    0.35
    අ
    0.35
    ContextCompat
    0.35
    hôtel
    0.35
    وص
    0.34
    ijnlijk
    0.34
    नाश
    0.34
     oxidación
    0.34
    POSITIVE LOGITS
     R
    0.50
     P
    0.43
     N
    0.43
    ('
    0.43
     T
    0.42
     W
    0.41
     d
    0.41
     о
    0.40
     D
    0.40
     x
    0.39
    Act Density 0.012%

    No Known Activations