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

    Neuronpedia

    INDEX
    Explanations

    operating system tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᒐ
    0.46
     alé
    0.42
     Rubber
    0.41
    ုပ်
    0.41
    CLOSE
    0.39
     resiliency
    0.38
     animé
    0.38
     Dél
    0.37
     waarop
    0.37
     passado
    0.37
    POSITIVE LOGITS
     phố
    0.42
     sólidos
    0.39
    beans
    0.39
    ologist
    0.38
    alach
    0.38
    𝙚
    0.37
     consistently
    0.37
    rologist
    0.37
     pouze
    0.37
    سكري
    0.37
    Act Density 0.000%

    No Known Activations