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

    Neuronpedia

    INDEX
    Explanations

    very + adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iendo
    0.46
     başlat
    0.44
     gospodar
    0.42
     istri
    0.41
    azione
    0.41
     seja
    0.41
    METHOD
    0.41
     forhold
    0.40
     bewegen
    0.40
     lichaam
    0.40
    POSITIVE LOGITS
     सारे
    0.45
     sums
    0.45
     large
    0.43
     amounts
    0.41
     arguably
    0.40
     amount
    0.40
     T
    0.38
     high
    0.38
    T
    0.38
     portions
    0.37
    Act Density 0.041%

    No Known Activations