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

    Neuronpedia

    INDEX
    Explanations

    specific numbers and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    edk
    0.43
    %@",
    0.42
    ed
    0.42
     Kreat
    0.41
     Elovl
    0.41
    ࿔
    0.40
    CLES
    0.38
     Interessen
    0.38
    <unused374>
    0.38
     Pist
    0.38
    POSITIVE LOGITS
    आई
    0.45
    펠
    0.44
    도
    0.40
    А
    0.39
    inn
    0.39
    if
    0.38
    да
    0.37
    ও
    0.37
    ina
    0.36
     наличие
    0.36
    Act Density 0.001%

    No Known Activations