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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    _kill
    -0.06
    ichte
    -0.06
    �
    -0.06
    Hover
    -0.06
     Woche
    -0.06
     staffer
    -0.06
    华
    -0.06
     ));
    -0.06
    лож
    -0.06
    POSITIVE LOGITS
    冬
    0.07
    [root
    0.06
    bins
    0.06
    (Log
    0.06
     konuştu
    0.06
     порядке
    0.06
     Rum
    0.06
    룹
    0.06
     claiming
    0.06
     Blob
    0.06
    Act Density 0.020%

    No Known Activations