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

    Neuronpedia

    INDEX
    Explanations

    emphasis or redaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कायदा
    0.47
    점을
    0.43
     unconsciously
    0.43
    も含
    0.43
     materialistic
    0.43
    Kost
    0.42
    廪
    0.42
    лювання
    0.42
    점이
    0.41
     helpless
    0.41
    POSITIVE LOGITS
     Puedes
    0.49
     Lorsque
    0.43
     რომელიც
    0.43
     resultado
    0.42
     referenced
    0.41
     llegó
    0.41
     eluted
    0.41
     från
    0.41
     emailed
    0.41
     которая
    0.40
    Act Density 0.003%

    No Known Activations