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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Encoding
    -0.07
     vídeos
    -0.07
    =log
    -0.07
    svm
    -0.06
    Chat
    -0.06
    _Il
    -0.06
    אירופה
    -0.06
    .embed
    -0.06
     Explosion
    -0.06
     refute
    -0.06
    POSITIVE LOGITS
    荷兰
    0.06
    ung
    0.06
    iw
    0.06
    ⤇
    0.06
    世界杯
    0.06
    剂量
    0.06
    划分
    0.06
    .field
    0.06
    雅
    0.06
    硪
    0.06
    Act Density 0.002%

    No Known Activations