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

    Neuronpedia

    INDEX
    Explanations

    presenting information or findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.63
     on
    1.42
    ва
    1.20
    า
    1.19
    리
    1.16
    ong
    1.14
    ü
    1.14
    ain
    1.13
    og
    1.10
     an
    1.09
    POSITIVE LOGITS
    present
    1.34
    Present
    1.16
    ad
    1.08
     Trois
    0.99
    Aile
    0.97
    AIN
    0.95
    is
    0.93
     dusk
    0.93
    У
    0.90
    IQUE
    0.89
    Act Density 0.026%

    No Known Activations