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

    Neuronpedia

    INDEX
    Explanations

    areas and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hop
    0.44
     "
    0.40
     '
    0.40
     Arth
    0.39
     ale
    0.38
     double
    0.38
     exhibited
    0.36
     Schä
    0.36
     seguramente
    0.36
     друго
    0.36
    POSITIVE LOGITS
    Areas
    0.45
    attiyam
    0.41
    áreas
    0.40
     AREAS
    0.39
    SubDirectory
    0.38
    面积
    0.37
    Structure
    0.37
    EPEND
    0.36
     площади
    0.36
    areas
    0.35
    Act Density 0.000%

    No Known Activations