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

    Neuronpedia

    INDEX
    Explanations

    Ships and naval activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     několika
    -0.07
    �
    -0.06
    HEY
    -0.06
    üstü
    -0.06
     Pope
    -0.06
    _started
    -0.06
    (pow
    -0.06
    卡
    -0.06
     Dudley
    -0.06
    (default
    -0.06
    POSITIVE LOGITS
    whelming
    0.07
     돌
    0.07
     displ
    0.06
    тий
    0.06
    ้งาน
    0.06
    роф
    0.06
     bosses
    0.06
     stringWithFormat
    0.06
    (pref
    0.06
     수정
    0.06
    Act Density 0.076%

    No Known Activations