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

    Neuronpedia

    INDEX
    Explanations

    randomized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shawn
    -0.07
    URLException
    -0.06
     tortured
    -0.06
     fright
    -0.06
    Map
    -0.06
     شد
    -0.06
     Mansion
    -0.06
     karşısında
    -0.06
     respectful
    -0.06
    _nv
    -0.06
    POSITIVE LOGITS
     farklı
    0.06
    �
    0.06
    ￣￣￣￣￣￣￣￣
    0.06
    :_
    0.06
     caravan
    0.06
    `
↵
    0.06
     abdom
    0.06
    사
    0.06
     payable
    0.06
     Lor
    0.06
    Act Density 0.010%

    No Known Activations