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

    Neuronpedia

    INDEX
    Explanations

    categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	buffer
    -0.07
     Be
    -0.07
    oming
    -0.07
    ه
    -0.07
    //!↵
    -0.07
    ever
    -0.07
    fid
    -0.06
    سير
    -0.06
    섞
    -0.06
    HIR
    -0.06
    POSITIVE LOGITS
     Pty
    0.08
     Latino
    0.07
    🕟
    0.07
    .Private
    0.07
     Silicon
    0.07
    产销
    0.07
    交通枢纽
    0.07
     academia
    0.07
     Filipino
    0.07
    _sg
    0.07
    Act Density 0.016%

    No Known Activations