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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auparavant
    -0.09
     ખાસ
    -0.08
     खास
    -0.08
     अर्थात
    -0.08
     включая
    -0.08
     विशेष
    -0.08
    。ただ
    -0.08
     cement
    -0.07
    Хот
    -0.07
    andez
    -0.07
    POSITIVE LOGITS
     المنت
    0.09
     toro
    0.08
    ytter
    0.08
     logró
    0.08
    update
    0.08
    isek
    0.08
    foobar
    0.07
     المست
    0.07
    olab
    0.07
    -sk
    0.07
    Act Density 0.252%

    No Known Activations