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

    Neuronpedia

    INDEX
    Explanations

    visuals and discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Các
    0.52
     Weitere
    0.52
     Некоторые
    0.51
    Οι
    0.47
     Additional
    0.47
     Συν
    0.46
     Utilisez
    0.46
     Políticas
    0.46
     Beberapa
    0.45
    Additional
    0.45
    POSITIVE LOGITS
     or
    0.54
     in
    0.52
     and
    0.52
     и
    0.45
     robes
    0.44
    ;
    0.42
     или
    0.40
     і
    0.38
     that
    0.37
     trousers
    0.37
    Act Density 0.000%

    No Known Activations