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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ческое
    0.44
    chens
    0.43
     அதிகரிக்க
    0.41
     دقیق
    0.40
    ometrically
    0.40
    _,
    0.39
    ЕНИЕ
    0.39
    クロマト
    0.39
    apanam
    0.39
    떻
    0.38
    POSITIVE LOGITS
    ("",
    0.65
    <>(
    0.57
    》（
    0.54
    ());
    0.54
     ();
    0.54
    ();
    0.52
    》(
    0.52
     ((
    0.52
    (-
    0.51
     ("",
    0.51
    Act Density 0.004%

    No Known Activations