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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accommodations
    -0.07
    yna
    -0.07
    超出
    -0.07
     참고
    -0.07
     bliss
    -0.07
     Gi
    -0.07
     공
    -0.07
     Sergio
    -0.07
    ício
    -0.07
    יס
    -0.07
    POSITIVE LOGITS
    ">↵
    0.07
    ">
    0.06
     لتح
    0.06
    _fx
    0.06
    泚
    0.06
     affected
    0.06
    />
    0.06
    )),↵
    0.06
    ()=>
    0.06
    河流
    0.06
    Act Density 0.002%

    No Known Activations