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

    Neuronpedia

    INDEX
    Explanations

    fresh paint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     serrated
    -0.82
    igneur
    -0.81
     hydrology
    -0.80
    ="@+
    -0.80
     Metab
    -0.77
    PhysRevLett
    -0.77
     tròn
    -0.77
     Abfall
    -0.77
    gini
    -0.77
    bling
    -0.77
    POSITIVE LOGITS
     paint
    3.31
     painting
    2.84
     Paint
    2.55
     painted
    2.55
    paint
    2.42
     Painting
    2.38
    Paint
    2.36
     paints
    2.30
    Painting
    2.25
    painting
    2.14
    Act Density 0.017%

    No Known Activations