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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ch
    -0.07
    answers
    -0.07
     опыт
    -0.07
    academic
    -0.06
    سية
    -0.06
    _direction
    -0.06
    이션
    -0.06
    (sm
    -0.06
    -manager
    -0.06
     halk
    -0.06
    POSITIVE LOGITS
    ilio
    0.06
     τ
    0.06
    Mate
    0.06
     Exiting
    0.06
     partition
    0.06
     episode
    0.06
     Baron
    0.06
    ，↵↵
    0.06
     آمار
    0.06
     Rit
    0.06
    Act Density 0.005%

    No Known Activations