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

    Neuronpedia

    INDEX
    Explanations

    each every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frances
    -0.07
    227
    -0.06
    нє
    -0.06
    221
    -0.06
    monkey
    -0.06
     út
    -0.06
     sage
    -0.06
     Bry
    -0.06
     warranted
    -0.06
    701
    -0.06
    POSITIVE LOGITS
    щин
    0.08
     склада
    0.07
    rowth
    0.07
    ACTION
    0.07
     climbs
    0.06
    ительность
    0.06
     معد
    0.06
    AO
    0.06
    .Book
    0.06
     pans
    0.06
    Act Density 0.023%

    No Known Activations