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

    Neuronpedia

    INDEX
    Explanations

    `Cargo.toml`, `tan`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estatales
    1.16
    führt
    1.08
    ro
    1.05
     podrían
    1.04
     konnten
    1.03
    บาง
    1.02
     asuntos
    1.00
     creen
    0.99
    yn
    0.97
     elección
    0.97
    POSITIVE LOGITS
    i
    1.35
    ে
    1.27
    ه
    1.13
    iiv
    1.10
    iencia
    1.04
     polished
    0.95
    ić
    0.91
     giddy
    0.89
     nodeId
    0.89
    iul
    0.88
    Act Density 0.001%

    No Known Activations