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

    Neuronpedia

    INDEX
    Explanations

    large

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "}}↵
    -0.07
    凌
    -0.07
     kdo
    -0.07
    ประโย
    -0.07
     TEntity
    -0.07
     pancakes
    -0.06
     reproduced
    -0.06
    _UNUSED
    -0.06
    -w
    -0.06
     Á
    -0.06
    POSITIVE LOGITS
     조금
    0.07
    orsch
    0.07
     만족
    0.06
     slight
    0.06
    /rc
    0.06
     قدر
    0.06
    灯
    0.06
    ันธ
    0.06
     soft
    0.06
     شهید
    0.06
    Act Density 0.038%

    No Known Activations