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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessures
    -0.08
     Ville
    -0.08
     secondes
    -0.08
     जी
    -0.07
     בפני
    -0.07
    .seconds
    -0.07
    .pl
    -0.07
     Having
    -0.07
     அல்ல
    -0.07
    jad
    -0.07
    POSITIVE LOGITS
     majority
    0.09
     порядок
    0.08
     मौका
    0.08
     footh
    0.08
     gamut
    0.08
     Majority
    0.08
     Mehrheit
    0.08
    uum
    0.08
     portion
    0.08
     foundation
    0.08
    Act Density 0.094%

    No Known Activations