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

    Neuronpedia

    INDEX
    Explanations

    oriental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Seriously
    -0.08
     Pump
    -0.07
     rode
    -0.07
     Ses
    -0.07
    classnames
    -0.07
    쥘
    -0.07
     kicked
    -0.07
     Lý
    -0.06
     Woody
    -0.06
     sleep
    -0.06
    POSITIVE LOGITS
    把它
    0.08
     그것을
    0.08
    ensors
    0.07
    彰
    0.07
    ).^
    0.07
    帮他
    0.07
     deterioration
    0.07
    :**
    0.07
    ARIABLE
    0.07
    orr
    0.07
    Act Density 0.005%

    No Known Activations