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

    Neuronpedia

    INDEX
    Explanations

    explanation followed by elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.47
     حضرت
    0.43
    ooled
    0.43
     নির্মিত
    0.43
    大的
    0.42
    rati
    0.41
     (
    0.41
     vär
    0.40
     hennes
    0.40
    Dude
    0.40
    POSITIVE LOGITS
    ͒
    0.48
     ongoing
    0.46
     mechanisms
    0.45
    mechanism
    0.44
     mononuclear
    0.44
     trụ
    0.43
    資
    0.43
     snowing
    0.42
     mechanism
    0.41
    仕組み
    0.41
    Act Density 0.004%

    No Known Activations