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

    Neuronpedia

    INDEX
    Explanations

    java collection instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ющиеся
    0.63
     வக
    0.59
    꽤
    0.58
     trữ
    0.56
     முக்கியமான
    0.54
     farmac
    0.54
     夕
    0.54
    啖
    0.53
    asionally
    0.51
    调研
    0.51
    POSITIVE LOGITS
    <>(
    1.52
    <>();
    1.37
    <>
    1.19
     <>
    1.09
    <>());
    0.97
    >()
    0.71
    >().
    0.71
     "-"
    0.70
    --;
    0.69
    >>()
    0.68
    Act Density 0.000%

    No Known Activations