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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ntag
    -0.06
    lab
    -0.06
     clan
    -0.06
    /s
    -0.06
    ｊ
    -0.06
     şeyi
    -0.06
     mong
    -0.06
     salvage
    -0.06
    embrance
    -0.06
    Sep
    -0.06
    POSITIVE LOGITS
     Lime
    0.08
    ')");↵
    0.07
    ']."
    0.07
    4
    0.07
     ウ
    0.06
    ']");↵
    0.06
     Проф
    0.06
    'icon
    0.06
    '];
    0.06
    (find
    0.06
    Act Density 0.001%

    No Known Activations