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

    Neuronpedia

    INDEX
    Explanations

    do good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urée
    0.22
     citations
    0.20
    CodeDict
    0.19
     IPCC
    0.19
     cues
    0.19
     τέ
    0.19
     snack
    0.19
     appetizers
    0.19
    urine
    0.19
     snacks
    0.18
    POSITIVE LOGITS
    诋
    0.17
    ло
    0.17
     actualidad
    0.16
     турган
    0.16
     ANOTHER
    0.16
     भरने
    0.16
     здраво
    0.16
     numerador
    0.16
    о
    0.16
    多的
    0.16
    Act Density 0.000%

    No Known Activations