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

    Neuronpedia

    INDEX
    Explanations

    oy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '?'
    -0.06
     theaters
    -0.06
     daddy
    -0.06
     Fer
    -0.06
     Kul
    -0.06
     будів
    -0.06
     AAA
    -0.06
    oustic
    -0.06
     Healing
    -0.06
    Ath
    -0.06
    POSITIVE LOGITS
     classmates
    0.07
     Moor
    0.07
    .pass
    0.07
    -alt
    0.07
    <section
    0.06
    recommended
    0.06
    Rank
    0.06
     attributable
    0.06
     troll
    0.06
     بای
    0.06
    Act Density 0.003%

    No Known Activations