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

    Neuronpedia

    INDEX
    Explanations

    cookies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.53
    ک
    0.51
    在
    0.50
    )
    0.49
    리
    0.49
     Verlauf
    0.48
    Q
    0.46
     Advertisement
    0.46
    य
    0.46
    и
    0.46
    POSITIVE LOGITS
    addItem
    0.49
    əri
    0.47
    kamer
    0.47
    avage
    0.46
    edDevice
    0.45
    endidikan
    0.44
    antal
    0.43
    டையே
    0.43
     soggy
    0.43
     murmured
    0.42
    Act Density 0.001%

    No Known Activations