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

    Neuronpedia

    INDEX
    Explanations

    belief, expectation, and knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     في
    0.39
    I
    0.39
     in
    0.38
    在
    0.38
    и
    0.38
    ﻟ
    0.37
    G
    0.37
    ，
    0.36
    да
    0.36
    ،
    0.35
    POSITIVE LOGITS
     been
    0.49
    ä
    0.48
     fertilisers
    0.44
     flavours
    0.40
    dL
    0.39
     licences
    0.39
    র
    0.39
     बड़े
    0.39
    る
    0.38
    ارى
    0.38
    Act Density 0.593%

    No Known Activations