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

    Neuronpedia

    INDEX
    Explanations

    yoga and/or exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formatted
    -0.08
    _metadata
    -0.08
    (filename
    -0.08
    .commit
    -0.08
     and
    -0.08
    )
    -0.08
    Har
    -0.07
    Metadata
    -0.07
    ),
    -0.07
    _perf
    -0.07
    POSITIVE LOGITS
     sympat
    0.09
     Slowly
    0.08
     intensely
    0.08
     sizing
    0.08
     próximas
    0.08
     doucement
    0.08
     substitutions
    0.08
     대신
    0.08
     Sonn
    0.08
     slightest
    0.08
    Act Density 0.005%

    No Known Activations