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

    Neuronpedia

    INDEX
    Explanations

    Website links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comput
    -0.07
     John
    -0.07
    �
    -0.06
     words
    -0.06
     Mary
    -0.06
     Sales
    -0.06
    -y
    -0.06
    ivity
    -0.06
    °С
    -0.06
     Provincial
    -0.06
    POSITIVE LOGITS
     Pawn
    0.06
    AsStream
    0.06
    _deposit
    0.06
     programu
    0.06
    áu
    0.06
    /jpeg
    0.06
    اگر
    0.05
     scholars
    0.05
     CString
    0.05
     Прот
    0.05
    Act Density 0.022%

    No Known Activations