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

    Neuronpedia

    INDEX
    Explanations

    articles and prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preempt
    -0.07
    폭
    -0.07
     هنا
    -0.07
    ilihan
    -0.06
    outs
    -0.06
    (PARAM
    -0.06
     dow
    -0.06
     FLAC
    -0.06
     교
    -0.06
     اليوم
    -0.06
    POSITIVE LOGITS
     vegetation
    0.07
     gas
    0.07
     constants
    0.06
    rrha
    0.06
    ією
    0.06
     inade
    0.06
    ’h
    0.06
    Los
    0.06
     Lap
    0.06
    يا
    0.06
    Act Density 0.005%

    No Known Activations