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

    Neuronpedia

    INDEX
    Explanations

    c/c++ include statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <
    0.42
    <
    0.40
     effector
    0.38
     sustent
    0.37
    энд
    0.37
     int
    0.36
     ajal
    0.36
     artefacts
    0.36
    のこ
    0.35
    修
    0.35
    POSITIVE LOGITS
    iostream
    0.55
    Liquid
    0.45
    ᴘ
    0.40
    urlopen
    0.40
     rangi
    0.39
    REG
    0.38
    Ꮲ
    0.38
    bits
    0.38
    Princ
    0.38
    zeichnung
    0.38
    Act Density 0.001%

    No Known Activations