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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helper
    -0.06
    322
    -0.06
    Rich
    -0.06
    ylinder
    -0.06
    _schema
    -0.06
     Thief
    -0.06
     freezes
    -0.06
    _fact
    -0.06
    anoia
    -0.06
    PARSE
    -0.06
    POSITIVE LOGITS
     Česko
    0.07
    @s
    0.07
    toString
    0.07
    .Co
    0.07
    만원입니다
    0.06
     seamlessly
    0.06
    .ct
    0.06
    (sel
    0.06
    voor
    0.06
     legitim
    0.06
    Act Density 0.005%

    No Known Activations