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

    Neuronpedia

    INDEX
    Explanations

    Character Map

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ވަ
    0.47
    ション
    0.47
    ochlorite
    0.47
     기초
    0.47
    নব
    0.46
    ס
    0.46
     NotImplemented
    0.45
     தேவை
    0.45
     tempHeader
    0.44
     ಅಧಿಕ
    0.43
    POSITIVE LOGITS
     picnics
    0.50
     lash
    0.45
     kimchi
    0.44
     frutas
    0.43
     attend
    0.43
     qua
    0.43
     attends
    0.43
     Eucalyptus
    0.42
    Voilà
    0.42
     an
    0.41
    Act Density 0.001%

    No Known Activations