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

    Neuronpedia

    INDEX
    Explanations

    code comments and file headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ший
    0.48
     duas
    0.42
     afectan
    0.41
    ifika
    0.41
    ográf
    0.41
    ším
    0.41
     dificuldades
    0.41
     dificultad
    0.41
     importancia
    0.41
     detener
    0.40
    POSITIVE LOGITS
     S
    0.51
     Copyright
    0.50
     E
    0.45
    BU
    0.45
     B
    0.44
     copyright
    0.43
     C
    0.43
    Copyright
    0.43
     T
    0.42
     D
    0.42
    Act Density 0.000%

    No Known Activations