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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crest
    -0.07
    (Rect
    -0.06
     fired
    -0.06
     oxidation
    -0.06
     contend
    -0.06
     hoàng
    -0.06
    :end
    -0.06
     nun
    -0.06
     сло
    -0.06
    traction
    -0.06
    POSITIVE LOGITS
     Sevent
    0.07
    <decltype
    0.07
    .period
    0.07
    웅
    0.07
    ế
    0.06
     这
    0.06
     WAN
    0.06
    (atom
    0.06
    حة
    0.06
     thưởng
    0.06
    Act Density 0.000%

    No Known Activations