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

    Neuronpedia

    INDEX
    Explanations

    database table creation syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    1.18
    +
    1.10
     +
    1.05
    1
    0.97
     '
    0.93
    and
    0.92
    -
    0.90
     (
    0.90
    (
    0.89
    !
    0.89
    POSITIVE LOGITS
     modelBuilder
    1.00
    漃
    0.95
     thửa
    0.94
     deceduto
    0.94
    椃
    0.93
     vendeur
    0.92
     chattel
    0.91
     vendita
    0.91
     grantor
    0.90
     responsabilità
    0.90
    Act Density 0.267%

    No Known Activations