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

    Neuronpedia

    INDEX
    Explanations

    pointing to specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.48
    8
    0.47
     www
    0.46
     सैकड़ों
    0.46
    T
    0.45
     hundreds
    0.45
    www
    0.44
     dozens
    0.43
    5
    0.43
    数百
    0.43
    POSITIVE LOGITS
     κάτι
    0.49
     motiv
    0.45
     konkrét
    0.45
     inclusivity
    0.45
     motiva
    0.44
    而非
    0.44
     appropriateness
    0.43
     impetus
    0.42
     noticia
    0.42
     houve
    0.42
    Act Density 0.525%

    No Known Activations