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

    Neuronpedia

    INDEX
    Explanations

    medical advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inya
    -0.08
     кул
    -0.08
     marketer
    -0.08
    ்ப்ப
    -0.08
     Oleh
    -0.07
    culator
    -0.07
     utiliser
    -0.07
     sisi
    -0.07
     menggunakan
    -0.07
     cens
    -0.07
    POSITIVE LOGITS
     reduces
    0.09
     zusätzlichen
    0.08
     induces
    0.08
     erhöht
    0.08
    Equivalent
    0.08
    导致
    0.08
     reduce
    0.08
     conducive
    0.08
     induce
    0.08
    极
    0.07
    Act Density 0.100%

    No Known Activations