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

    Neuronpedia

    INDEX
    Explanations

    permutations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     توص
    -0.08
     uma
    -0.08
    姿
    -0.08
    healthy
    -0.07
    tun
    -0.07
     ];↵↵
    -0.07
     bewa
    -0.07
     destabil
    -0.07
     healthy
    -0.07
    ിച്ചത
    -0.07
    POSITIVE LOGITS
     únicos
    0.09
     distint
    0.09
    astos
    0.08
     distinctions
    0.08
     diff
    0.08
     confusing
    0.08
     permutations
    0.08
    aghetti
    0.08
     duplicates
    0.08
     vegna
    0.08
    Act Density 0.023%

    No Known Activations