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

    Neuronpedia

    INDEX
    Explanations

    Asking questions/help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SHORT
    -0.07
    רצ
    -0.07
    _email
    -0.06
    Thought
    -0.06
    _multiply
    -0.06
    lobals
    -0.06
     square
    -0.06
    �
    -0.06
    .place
    -0.06
    file
    -0.06
    POSITIVE LOGITS
    cee
    0.08
    ńs
    0.07
    مؤسسة
    0.07
     millennials
    0.07
     rab
    0.07
    .Other
    0.07
    流出
    0.07
    猁
    0.07
     Dems
    0.06
     работе
    0.06
    Act Density 0.108%

    No Known Activations