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

    Neuronpedia

    INDEX
    Explanations

    c++ include statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    boldsymbol
    0.43
    漕
    0.43
    ানিতে
    0.41
     কাছে
    0.40
    রণ
    0.38
    ாத
    0.38
    तेश
    0.38
    *((*
    0.38
    ILI
    0.38
    iserum
    0.38
    POSITIVE LOGITS
     <
    1.02
    <
    0.89
    <>
    0.69
     "../
    0.64
     "./
    0.63
    "./
    0.62
     <>
    0.61
    <\
    0.59
    ＜
    0.57
    <_
    0.56
    Act Density 0.007%

    No Known Activations