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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devastating
    -0.07
    _problem
    -0.06
     тр
    -0.06
     trying
    -0.06
     Çocuk
    -0.06
     التع
    -0.06
     wast
    -0.06
     сил
    -0.06
    ικές
    -0.06
     Workplace
    -0.06
    POSITIVE LOGITS
    POSIT
    0.07
    lint
    0.06
     TKey
    0.06
    021
    0.06
    ♀♀
    0.06
     Rut
    0.06
     Wind
    0.06
     groot
    0.06
    ुपय
    0.06
    tree
    0.06
    Act Density 0.020%

    No Known Activations