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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quierda
    -0.09
    ponses
    -0.09
    spapers
    -0.08
    asured
    -0.08
    epen
    -0.08
    راسة
    -0.08
    šnja
    -0.08
     Mansion
    -0.08
    pon
    -0.08
    spaper
    -0.08
    POSITIVE LOGITS
    》第
    0.08
     of
    0.08
     inadvertently
    0.08
     substantially
    0.07
    第二
    0.07
     Vorte
    0.07
     fundamentally
    0.07
     dramatically
    0.07
     multiplied
    0.07
    (&:
    0.07
    Act Density 0.037%

    No Known Activations