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

    Neuronpedia

    INDEX
    Explanations

    `packages pickle`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    玼
    0.44
     BLUENRG
    0.40
    
    0.40
    цією
    0.39
    甴
    0.39
    苌
    0.39
     BlueprintName
    0.39
    简洁
    0.38
     Puoi
    0.38
    总是
    0.38
    POSITIVE LOGITS
     divest
    0.44
     compatriots
    0.40
     kindred
    0.40
     ashore
    0.40
     mischiev
    0.40
     chaf
    0.40
     frock
    0.39
     spirits
    0.37
     vanqu
    0.37
     endangering
    0.37
    Act Density 0.000%

    No Known Activations