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

    Neuronpedia

    INDEX
    Explanations

    job title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ták
    0.93
    слава
    0.91
    уд
    0.89
    tug
    0.88
    𝒋
    0.87
    쭌
    0.86
    ды
    0.86
    宻
    0.84
    tä
    0.84
     уены
    0.84
    POSITIVE LOGITS
     menu
    0.85
    。
    0.77
     vest
    0.73
     cache
    0.71
     detail
    0.70
    >
    0.70
    ，
    0.70
     div
    0.69
    0
    0.68
     time
    0.68
    Act Density 0.000%

    No Known Activations