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

    Neuronpedia

    INDEX
    Explanations

    Technical writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     покол
    -0.07
    Thumbnail
    -0.07
     incorpor
    -0.06
    SUP
    -0.06
    uil
    -0.06
    zení
    -0.06
     коміс
    -0.06
    _sur
    -0.06
     поход
    -0.06
    ambiguous
    -0.06
    POSITIVE LOGITS
    备份
    0.07
     م
    0.06
     imkan
    0.06
     **
    0.06
     Som
    0.06
    <Integer
    0.06
    限制
    0.06
    -et
    0.06
    end
    0.06
    เง
    0.06
    Act Density 0.000%

    No Known Activations