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

    Neuronpedia

    INDEX
    Explanations

    predict outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴵ
    0.46
    ▉
    0.45
     നിരവധി
    0.45
    ✎
    0.45
    IELD
    0.44
     أيضًا
    0.44
     গ্রস্থ
    0.43
    adrenaline
    0.43
     তাড়াতাড়ি
    0.43
    limegreen
    0.42
    POSITIVE LOGITS
     matrices
    0.47
     chandeliers
    0.45
     ON
    0.45
     railroads
    0.43
     compagnies
    0.43
     mortars
    0.42
     vases
    0.42
     roads
    0.41
    ts
    0.41
     barb
    0.41
    Act Density 0.012%

    No Known Activations