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

    Neuronpedia

    INDEX
    Explanations

    exclamation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '^
    -0.06
    )sender
    -0.06
    ffmpeg
    -0.06
    átku
    -0.06
    configs
    -0.06
    ‐'
    -0.06
    :w
    -0.06
    -N
    -0.06
    emm
    -0.06
    hidden
    -0.06
    POSITIVE LOGITS
    Damage
    0.06
     발
    0.06
    !!!↵
    0.06
    ccione
    0.06
    咲
    0.06
     ruled
    0.06
    ẩn
    0.06
    Second
    0.06
    (det
    0.06
    !?
    0.06
    Act Density 0.041%

    No Known Activations