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

    Neuronpedia

    INDEX
    Explanations

    exponents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sudden
    -0.07
     Radio
    -0.07
     Hospital
    -0.07
    rxjs
    -0.07
    فى
    -0.07
     Explosion
    -0.07
    监察
    -0.07
    tern
    -0.07
    Until
    -0.07
    _override
    -0.07
    POSITIVE LOGITS
     lastname
    0.08
    <Array
    0.07
    ()};↵
    0.07
    ()=="
    0.07
     כש
    0.07
     экон
    0.06
     unitOfWork
    0.06
    気軽に
    0.06
     `\
    0.06
    月至
    0.06
    Act Density 0.006%

    No Known Activations