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

    Neuronpedia

    INDEX
    Explanations

    vacuum, unknown, or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auguri
    0.50
     distinta
    0.50
     místě
    0.49
    водится
    0.49
     electrol
    0.49
     אחרי
    0.48
    വധി
    0.48
     ابتدا
    0.47
    MktCap
    0.47
     ecu
    0.47
    POSITIVE LOGITS
    F
    0.55
    ers
    0.52
    S
    0.45
    geon
    0.44
    orak
    0.44
    垠
    0.44
    illers
    0.42
    <0x87>
    0.42
    int
    0.42
    s
    0.41
    Act Density 0.001%

    No Known Activations