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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -rock
    -0.08
     Agency
    -0.08
     rock
    -0.08
     Balanced
    -0.07
     hennes
    -0.07
    Balanced
    -0.07
     Bil
    -0.07
    Guaranteed
    -0.07
     Rock
    -0.07
    -band
    -0.07
    POSITIVE LOGITS
    IONE
    0.10
    ütt
    0.08
    _RESULT
    0.08
     doj
    0.08
    cio
    0.08
    ผล
    0.08
     एहि
    0.08
    ormány
    0.07
     организации
    0.07
    QRSTUVWXYZ
    0.07
    Act Density 0.056%

    No Known Activations