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

    Neuronpedia

    INDEX
    Explanations

    code comments and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𓆏
    -2.34
     rése
    -2.17
    傒
    -2.14
     incrí
    -2.11
     工房
    -2.08
     célè
    -2.03
     sés
    -2.02
    ⛦
    -2.02
     ardu
    -2.00
    饜
    -2.00
    POSITIVE LOGITS
     to
    2.52
     just
    2.31
     more
    2.09
     all
    2.03
     A
    1.98
     In
    1.98
     D
    1.95
     Just
    1.94
     F
    1.92
     What
    1.91
    Act Density 0.007%

    No Known Activations