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

    Neuronpedia

    INDEX
    Explanations

    hybrid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMS
    -0.07
    ежду
    -0.07
     curiosity
    -0.06
     fitness
    -0.06
     Japanese
    -0.06
    еп
    -0.06
     Founder
    -0.06
    stretch
    -0.06
     aft
    -0.06
    isc
    -0.06
    POSITIVE LOGITS
     instantiate
    0.07
     NotFoundException
    0.06
    .getAction
    0.06
    banana
    0.06
    redd
    0.06
     земли
    0.06
     لدي
    0.06
    วน
    0.06
     RDD
    0.06
    xeb
    0.06
    Act Density 0.044%

    No Known Activations