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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    альне
    -0.06
     yu
    -0.06
    -average
    -0.06
    ’i
    -0.06
     демон
    -0.06
    iday
    -0.06
     prevail
    -0.06
     formed
    -0.06
    .onPause
    -0.06
     многих
    -0.06
    POSITIVE LOGITS
     Tet
    0.07
    ack
    0.06
    ốt
    0.06
     packet
    0.06
    ounding
    0.06
     소리
    0.06
    OX
    0.06
    -inf
    0.06
     Founder
    0.06
    hythm
    0.06
    Act Density 0.024%

    No Known Activations