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

    Neuronpedia

    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _User
    -0.07
    _Work
    -0.06
    ינג
    -0.06
     geschichten
    -0.06
    尴尬
    -0.06
     Teddy
    -0.06
     Orwell
    -0.06
     Minerals
    -0.06
    _TXT
    -0.06
    逝
    -0.06
    POSITIVE LOGITS
    Default
    0.10
    评委
    0.07
     link
    0.07
     inoc
    0.07
    墈
    0.07
     separates
    0.07
    venue
    0.07
    _USE
    0.06
    戥
    0.06
    猄
    0.06
    Act Density 0.001%

    No Known Activations