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

    Neuronpedia

    INDEX
    Explanations

    end of the world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.73
    들이
    0.73
    тва
    0.73
     νέα
    0.72
    с
    0.71
    ᑯ
    0.71
    ва
    0.70
     научных
    0.70
     нового
    0.70
     роль
    0.70
    POSITIVE LOGITS
    >
    0.96
    ')
    0.75
    ON
    0.75
    Error
    0.69
    ad
    0.68
    File
    0.68
     ON
    0.68
    adito
    0.67
    Era
    0.67
    ")
    0.66
    Act Density 0.000%

    No Known Activations