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

    Neuronpedia

    INDEX
    Explanations

    ABC points in geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aliya
    0.46
    嵌套
    0.45
    <unused89>
    0.44
    ⬤
    0.44
    파트
    0.44
    多种
    0.43
    疙
    0.43
    నాలను
    0.42
    রাজনৈতিক
    0.42
     бясплатна
    0.42
    POSITIVE LOGITS
     C
    0.58
     B
    0.54
    on
    0.47
    C
    0.46
     D
    0.45
     O
    0.45
     periphery
    0.45
    }
    0.44
    B
    0.44
     himself
    0.43
    Act Density 0.009%

    No Known Activations