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

    Neuronpedia

    INDEX
    Explanations

    words after sur, row, columns, and string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laboratory
    0.44
     cellulose
    0.43
    Laboratory
    0.42
     shelter
    0.41
    ilibrium
    0.39
     combing
    0.39
    TRI
    0.38
    Mileage
    0.38
    laboratory
    0.38
    hte
    0.38
    POSITIVE LOGITS
    ₲
    0.47
     Dharm
    0.46
    éfonos
    0.45
     força
    0.45
     destrucción
    0.45
     arquivos
    0.44
     archivo
    0.44
     तला
    0.44
    𝑺
    0.44
     mencion
    0.43
    Act Density 0.002%

    No Known Activations