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

    Neuronpedia

    INDEX
    Explanations

    J

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dt
    -0.07
    ①
    -0.06
    ==============
    -0.06
     Convert
    -0.06
     Peters
    -0.06
    Radio
    -0.06
    84
    -0.06
    SUCCESS
    -0.06
    ylvania
    -0.06
    opez
    -0.06
    POSITIVE LOGITS
     вис
    0.08
     getIndex
    0.07
    탁
    0.07
    젝
    0.06
     je
    0.06
     Kanye
    0.06
     시즌
    0.06
    _Il
    0.06
    CLLocation
    0.06
    CCI
    0.06
    Act Density 0.006%

    No Known Activations