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

    Neuronpedia

    INDEX
    Explanations

    comma followed by description or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.47
    2
    0.46
    ו
    0.44
    H
    0.42
    The
    0.39
    the
    0.39
    S
    0.38
    W
    0.38
    ↵↵↵↵
    0.37
    ed
    0.35
    POSITIVE LOGITS
     bungalows
    0.32
    㧋
    0.30
    Fps
    0.30
     bunnies
    0.30
     chubby
    0.29
     musicales
    0.29
     다르
    0.29
    氛
    0.28
    cias
    0.28
     wineries
    0.28
    Act Density 3.411%

    No Known Activations