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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +'.
    -0.06
    ρεί
    -0.06
     θε
    -0.06
    secutive
    -0.06
     Lv
    -0.06
     svě
    -0.06
    véd
    -0.06
    nivel
    -0.06
    problem
    -0.06
    udence
    -0.06
    POSITIVE LOGITS
     slug
    0.08
     anon
    0.07
     easier
    0.07
     Shutdown
    0.06
     namoro
    0.06
     overhead
    0.06
     declined
    0.06
    urger
    0.06
     sz
    0.06
     Bylo
    0.06
    Act Density 0.000%

    No Known Activations