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

    Neuronpedia

    INDEX
    Explanations

    e.g.,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phần
    1.17
    &&\
    1.05
    sticker
    1.04
    ence
    1.00
     gelar
    0.99
    isEqualTo
    0.99
     desem
    0.98
    у
    0.93
     tổ
    0.91
    ことになる
    0.90
    POSITIVE LOGITS
     dopamine
    1.23
    avour
    1.10
    iiv
    1.07
    icient
    1.07
     $:
    1.06
     beacons
    1.06
    喃
    1.06
    ளாக்
    1.05
     keypad
    1.05
    Ĕ
    1.04
    Act Density 0.080%

    No Known Activations