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

    Neuronpedia

    INDEX
    Explanations

    no bearing on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.42
    5
    0.40
    Conversion
    0.39
    Example
    0.38
     complex
    0.38
     conversion
    0.38
    EXAMPLE
    0.38
    USA
    0.37
     theological
    0.37
     থাকতেন
    0.37
    POSITIVE LOGITS
    DeathRecord
    0.42
    ╧
    0.41
    $('
    0.39
    🍲
    0.39
    +',
    0.38
     fonbet
    0.38
     কার্য
    0.38
    adiya
    0.38
    効
    0.37
     фон
    0.37
    Act Density 0.000%

    No Known Activations