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

    Neuronpedia

    INDEX
    Explanations

    or Spanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     T
    1.31
     C
    1.30
     S
    1.16
     D
    1.14
    ﺭ
    1.13
     U
    1.05
    ة
    1.05
     (
    1.04
     O
    1.04
     игре
    1.04
    POSITIVE LOGITS
    도를
    1.30
    lieu
    1.24
    multiply
    1.17
    webview
    1.17
     pudiera
    1.16
    motors
    1.16
     жөнүндө
    1.16
    bev
    1.13
    도는
    1.13
    പ്പറ
    1.13
    Act Density 0.000%

    No Known Activations