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

    Neuronpedia

    INDEX
    Explanations

    technical documentation examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crept
    0.38
    orez
    0.35
     decreed
    0.35
     instilled
    0.35
    ূল্যে
    0.34
     prayed
    0.33
     calmed
    0.33
    स्टल
    0.32
     didn
    0.32
    hehi
    0.32
    POSITIVE LOGITS
     miscellaneous
    0.38
     NOTE
    0.34
    Note
    0.33
    vij
    0.33
     permutations
    0.32
    。
    0.32
    Referencias
    0.32
     notebooks
    0.32
    “”
    0.32
     사용할
    0.31
    Act Density 0.003%

    No Known Activations