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

    Neuronpedia

    INDEX
    Explanations

    keyword suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    น
    1.15
    ో
    1.00
    oretically
    0.98
    িয়া
    0.91
    िड
    0.90
    واه
    0.89
    iš
    0.89
    ેલ
    0.88
    bardziej
    0.88
     türlü
    0.87
    POSITIVE LOGITS
     experi
    1.21
     electrocardi
    1.12
     eczema
    1.08
     pneumonia
    1.05
     railings
    1.04
    se
    1.02
     petal
    1.02
     radiographs
    1.02
     calipers
    0.99
     evaporation
    0.98
    Act Density 0.369%

    No Known Activations