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

    Neuronpedia

    INDEX
    Explanations

    conciseness and precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기본
    0.52
    ומי
    0.42
     comprens
    0.42
    桠
    0.41
    🥢
    0.40
    。
    0.39
    웡
    0.39
     básico
    0.39
     मूलभूत
    0.39
    ዋል።
    0.38
    POSITIVE LOGITS
     phosphorylated
    0.40
    amsmath
    0.38
     produktu
    0.38
    entgen
    0.38
    소서
    0.38
    invoke
    0.38
     وصحبه
    0.37
     компет
    0.37
     sangre
    0.37
     senyawa
    0.37
    Act Density 0.032%

    No Known Activations