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

    Neuronpedia

    INDEX
    Explanations

    look

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    武侠
    -0.08
     semester
    -0.07
    emarks
    -0.07
    公園
    -0.07
    -simple
    -0.07
     SOS
    -0.07
    nad
    -0.07
    _logo
    -0.07
    -terminal
    -0.07
    ˆ
    -0.07
    POSITIVE LOGITS
    >alert
    0.07
    熬
    0.07
     إنه
    0.07
    邬
    0.06
    宜宾
    0.06
    ῆ
    0.06
     StringUtil
    0.06
     contentValues
    0.06
     �
    0.06
    별
    0.06
    Act Density 0.072%

    No Known Activations