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

    Neuronpedia

    INDEX
    Explanations

    prepositions and common articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्ड
    0.41
    我們會
    0.41
    wpilib
    0.40
    вчи
    0.40
    我們要
    0.39
    ശ
    0.38
    ლე
    0.38
     misura
    0.38
    程式
    0.37
    nilai
    0.37
    POSITIVE LOGITS
    Spring
    0.44
     accred
    0.43
    ంబే
    0.42
     Psychology
    0.41
    Oriental
    0.41
    Jazz
    0.41
    vocals
    0.40
     Jazz
    0.40
    オブ
    0.39
     McK
    0.38
    Act Density 0.000%

    No Known Activations