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

    Neuronpedia

    INDEX
    Explanations

    idae

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boston
    -0.07
    献
    -0.07
    -html
    -0.07
    ele
    -0.06
    Episode
    -0.06
    (interp
    -0.06
     RADIO
    -0.06
     samostat
    -0.06
    Boston
    -0.06
     honors
    -0.06
    POSITIVE LOGITS
    ﾆﾆ
    0.07
     lub
    0.06
    たし
    0.06
     awaits
    0.06
     payload
    0.06
     nak
    0.06
     /.
    0.06
     bub
    0.06
     Sorry
    0.06
    gateway
    0.06
    Act Density 0.003%

    No Known Activations