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

    Neuronpedia

    INDEX
    Explanations

    function definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    অর্থাৎ
    0.42
    셔서
    0.38
     diastolic
    0.36
     綿
    0.36
    FORMAN
    0.35
     효과
    0.35
     cavitation
    0.35
     帽
    0.35
     Фургала
    0.35
     wikipagina
    0.34
    POSITIVE LOGITS
    if
    0.50
    max
    0.45
    ↵
    0.39
    are
    0.38
    var
    0.38
    import
    0.37
    app
    0.37
    try
    0.36
    auto
    0.36
    #[
    0.36
    Act Density 0.055%

    No Known Activations