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

    Neuronpedia

    INDEX
    Explanations

    A/B or fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catalyst
    1.19
     crunch
    1.18
     optimizing
    1.18
     minimalist
    1.14
     catalysts
    1.13
     spreadsheets
    1.13
     usability
    1.11
     whimsical
    1.08
     troubleshooting
    1.07
     crafting
    1.07
    POSITIVE LOGITS
    etc
    1.48
    x
    1.36
    data
    1.33
    S
    1.31
    E
    1.30
    p
    1.30
    c
    1.28
    C
    1.27
    m
    1.25
    return
    1.24
    Act Density 0.340%

    No Known Activations