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

    Neuronpedia

    INDEX
    Explanations

    web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bad
    -0.07
    사이
    -0.07
     všechny
    -0.07
     BELOW
    -0.07
    _PACKAGE
    -0.07
     distract
    -0.07
    (operator
    -0.07
     průběhu
    -0.07
    !),
    -0.06
    Ru
    -0.06
    POSITIVE LOGITS
     Painter
    0.07
    Resultado
    0.06
    Comparable
    0.06
    ोश
    0.06
    wick
    0.06
     Sheriff
    0.06
     displ
    0.06
     Archae
    0.06
     spear
    0.06
     sheriff
    0.06
    Act Density 0.000%

    No Known Activations