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

    Neuronpedia

    INDEX
    Explanations

    works and management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glycine
    0.41
     साबित
    0.39
     tonnes
    0.38
     cyclohexane
    0.38
    ^(
    0.38
     Boa
    0.38
     सेल्सियस
    0.38
     contextos
    0.38
    頰
    0.37
     ouv
    0.36
    POSITIVE LOGITS
    тиви
    0.46
     prudent
    0.43
    泯
    0.43
     bias
    0.42
    MORDOR
    0.41
     Sustainable
    0.39
     Yet
    0.38
     बनानी
    0.37
     understandable
    0.37
    udin
    0.37
    Act Density 0.000%

    No Known Activations