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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math environments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beet
    0.88
     beets
    0.73
     wafer
    0.72
     wafers
    0.70
     gotas
    0.69
    陉
    0.69
     resign
    0.68
     beetroot
    0.68
     spinach
    0.68
     COMPOUNDS
    0.67
    POSITIVE LOGITS
    नहीं
    0.78
    ∶
    0.70
    על
    0.69
    ăm
    0.69
     didn
    0.69
     לא
    0.69
     tidak
    0.67
    รร
    0.66
    Didn
    0.66
    :=
    0.65
    Act Density 0.000%

    No Known Activations