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

    Neuronpedia

    INDEX
    Explanations

    symbols in code and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etheless
    0.33
     temporary
    0.33
     前
    0.32
     স্থায়ী
    0.32
     suo
    0.32
     the
    0.32
     produzido
    0.31
     二
    0.31
     অস্থায়ী
    0.31
    ercicio
    0.31
    POSITIVE LOGITS
    न्यास
    0.41
    setLookAndFeel
    0.40
    न्या
    0.39
    мей
    0.39
    खे
    0.37
    daar
    0.37
    ooky
    0.37
     niacin
    0.36
    лов
    0.36
    frow
    0.36
    Act Density 0.001%

    No Known Activations