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

    Neuronpedia

    INDEX
    Explanations

    ** **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baseline
    0.47
    ᇂ
    0.47
    -
    0.46
     convention
    0.45
     conventional
    0.45
     inclusion
    0.44
    বে
    0.43
     classroom
    0.43
    mobile
    0.43
     healthy
    0.43
    POSITIVE LOGITS
     aktiviert
    0.46
     വ്യക്തി
    0.46
    បុ
    0.44
     irão
    0.44
     bequeathed
    0.44
     обратно
    0.44
     zod
    0.43
     అత్య
    0.43
    ថ្ង
    0.43
     উদ্দেশ্যে
    0.42
    Act Density 0.005%

    No Known Activations