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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deprec
    0.37
     bettors
    0.36
    ButtonPressed
    0.34
     observations
    0.34
     sledge
    0.34
     user
    0.33
     dials
    0.33
     superiors
    0.33
    ڈیو
    0.33
    leting
    0.33
    POSITIVE LOGITS
     Also
    0.52
    ).
    0.49
     Emphasis
    0.47
     Также
    0.46
    .).
    0.45
     Examples
    0.45
    )…
    0.44
    )..
    0.43
     Editions
    0.42
     Trouvez
    0.42
    Act Density 0.067%

    No Known Activations