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

    Neuronpedia

    INDEX
    Explanations

    warranties and disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nut
    -0.08
    .prevent
    -0.08
    Seed
    -0.07
     تمن
    -0.07
    Bootstrap
    -0.07
     tariffs
    -0.07
    Confidence
    -0.07
     Kost
    -0.07
    mun
    -0.07
     nut
    -0.07
    POSITIVE LOGITS
     encounters
    0.09
    ்ப
    0.09
     podľa
    0.09
     bran
    0.08
     кл
    0.08
    ்ப்ப
    0.08
     əs
    0.08
     ઉત્ત
    0.08
     podle
    0.08
     скач
    0.08
    Act Density 0.002%

    No Known Activations