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

    Neuronpedia

    INDEX
    Explanations

    `__name__` Python variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     œuvres
    0.50
     بیماری
    0.47
     Similar
    0.47
     νέα
    0.46
     insights
    0.46
     Behavior
    0.45
    ларни
    0.45
    лар
    0.45
    ک
    0.45
     chimiques
    0.45
    POSITIVE LOGITS
     Bundest
    0.47
    ajati
    0.46
     நாட்க
    0.45
     पटक
    0.45
    atthakath
    0.44
     リン
    0.44
     rakh
    0.43
     seleccionar
    0.43
     Dienstag
    0.42
     Abuja
    0.42
    Act Density 0.001%

    No Known Activations