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

    Neuronpedia

    INDEX
    Explanations

    lists and categorizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secondi
    0.42
     secondly
    0.38
     вто
    0.37
    Escolh
    0.37
    reement
    0.36
    恹
    0.36
     second
    0.36
     ఎదు
    0.35
     Hoskins
    0.35
     الثانيه
    0.35
    POSITIVE LOGITS
    Q
    0.58
    How
    0.47
    1
    0.45
     Q
    0.44
    question
    0.43
     How
    0.41
    م
    0.41
    Pol
    0.41
    Rachel
    0.41
    Sorry
    0.40
    Act Density 0.000%

    No Known Activations