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

    Neuronpedia

    INDEX
    Explanations

    specific word continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وړاندوینه
    0.50
     Houston
    0.49
     recognizes
    0.47
     সেনা
    0.46
    <0x0E>
    0.45
     दरम्यान
    0.45
     depressed
    0.44
    امة
    0.44
    sadpoetry
    0.44
     }\
    0.44
    POSITIVE LOGITS
    و
    0.49
    Kale
    0.48
    Atlant
    0.47
    Reform
    0.46
    let
    0.46
    les
    0.45
    Tour
    0.45
    lais
    0.45
    TOUR
    0.44
    Cl
    0.44
    Act Density 0.000%

    No Known Activations