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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     아침
    -0.07
    774
    -0.07
     目
    -0.07
     Fisheries
    -0.07
     corpor
    -0.06
    ЛО
    -0.06
     koneč
    -0.06
     Todos
    -0.06
     prin
    -0.06
     arr
    -0.06
    POSITIVE LOGITS
    retch
    0.06
     loophole
    0.06
    ฏ
    0.06
    ็นผ
    0.06
    -ish
    0.06
    .flex
    0.06
    .panelControl
    0.06
    진
    0.06
    -transition
    0.06
    есть
    0.06
    Act Density 0.033%

    No Known Activations