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

    Neuronpedia

    INDEX
    Explanations

    say "slices"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Storm
    -0.12
     Storm
    -0.11
     storm
    -0.10
    storm
    -0.09
     storms
    -0.09
     wars
    -0.09
     bettor
    -0.09
    storms
    -0.09
     journ
    -0.09
    Veh
    -0.08
    POSITIVE LOGITS
     slices
    0.60
     slice
    0.55
    (slice
    0.54
    Slices
    0.52
    _slice
    0.52
    slice
    0.51
    Slice
    0.50
     Slice
    0.49
     slicing
    0.49
     sliced
    0.48
    Act Density 0.034%

    No Known Activations