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

    Neuronpedia

    INDEX
    Explanations

    your code/application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parser
    0.68
     version
    0.66
    loader
    0.65
     sacré
    0.65
     pilgrimage
    0.64
    稱為
    0.64
    ന്ധ
    0.64
     graag
    0.63
    壇
    0.63
    legung
    0.63
    POSITIVE LOGITS
     Have
    0.68
    คะ
    0.68
    ?
    0.63
     बहा
    0.63
    在意
    0.62
    ?“
    0.62
    clockwise
    0.61
     Allies
    0.61
     Divers
    0.61
    computer
    0.61
    Act Density 0.226%

    No Known Activations