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

    Neuronpedia

    INDEX
    Explanations

    JSON structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ();//
    0.72
    %；
    0.71
    ();
    0.71
    zuoye
    0.69
    ()">
    0.68
    %;
    0.64
    %。
    0.63
    ٪
    0.63
     ();
    0.62
    奻
    0.62
    POSITIVE LOGITS
    "
    0.77
    ]
    0.67
    သမ
    0.64
    ”
    0.64
    ame
    0.61
    )
    0.60
     घेण्यासाठी
    0.60
    ographe
    0.59
     "
    0.58
     ""
    0.57
    Act Density 0.007%

    No Known Activations