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

    Neuronpedia

    INDEX
    Explanations

    Permit Establishment Rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hectares
    1.18
    suk
    1.15
    Despite
    1.15
    Generating
    1.11
     khaki
    1.10
    +"
    1.10
    %%%%%%%%%%%%%%%%
    1.09
    perature
    1.09
    ']))
    1.09
    ‘’
    1.08
    POSITIVE LOGITS
    인을
    1.06
    是
    1.02
    ্লাই
    1.00
    인은
    0.99
    ت
    0.99
    是将
    0.99
    ını
    0.97
     almak
    0.97
    td
    0.94
    eine
    0.94
    Act Density 0.001%

    No Known Activations