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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    闲
    -0.07
    [args
    -0.07
     myself
    -0.06
    meeting
    -0.06
    winter
    -0.06
    ється
    -0.06
     زم
    -0.06
     AES
    -0.06
    .words
    -0.06
    偷
    -0.06
    POSITIVE LOGITS
    ละคร
    0.07
     surprise
    0.06
    PARTMENT
    0.06
    คร
    0.06
    ILITY
    0.06
    ‌های
    0.06
     �
    0.06
     REPL
    0.06
    팔
    0.06
     ماي
    0.06
    Act Density 0.057%

    No Known Activations