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

    Neuronpedia

    INDEX
    Explanations

    paid than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    စိတ်အပိုင်း
    0.49
     justo
    0.47
    %，
    0.46
    栝
    0.46
     Remembering
    0.46
     WORDS
    0.45
     mostr
    0.44
     penyebab
    0.44
     Panasonic
    0.44
     Bringing
    0.44
    POSITIVE LOGITS
    є
    0.48
    ide
    0.43
    踴
    0.43
    land
    0.43
    eta
    0.42
    bilir
    0.42
    ógy
    0.42
    ety
    0.41
    Gap
    0.41
    Inverse
    0.41
    Act Density 0.002%

    No Known Activations