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

    Neuronpedia

    INDEX
    Explanations

    positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     другого
    0.47
     самого
    0.45
     other
    0.44
     несо
    0.43
     других
    0.41
    team
    0.40
     COUP
    0.40
     BOTH
    0.39
     both
    0.38
     comparatively
    0.38
    POSITIVE LOGITS
     Amended
    0.44
     alumnos
    0.42
     iniziamo
    0.42
     dix
    0.40
     อาจารย์
    0.40
    திகள்
    0.40
     tramite
    0.40
    上线
    0.40
     syllabus
    0.40
     alunos
    0.39
    Act Density 0.001%

    No Known Activations