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

    Neuronpedia

    INDEX
    Explanations

    levels and grades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diarrhoea
    1.83
     anaemia
    1.73
     anemia
    1.69
     hulle
    1.68
     antibiotic
    1.65
     Digests
    1.62
     antibiotics
    1.62
    おお
    1.54
     diuretic
    1.54
    erler
    1.51
    POSITIVE LOGITS
    notch
    2.30
     tiers
    2.13
    DOUT
    2.06
    ويات
    2.04
     notch
    2.03
    7
    1.99
    gallant
    1.96
    grade
    1.95
    าตุ
    1.92
    层的
    1.90
    Act Density 0.262%

    No Known Activations