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

    Neuronpedia

    INDEX
    Explanations

    foreign language suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ier
    0.67
    at
    0.66
    iert
    0.61
    has
    0.59
    fält
    0.59
    end
    0.58
    ito
    0.58
    funktion
    0.57
    hot
    0.57
     it
    0.56
    POSITIVE LOGITS
    的
    0.82
    의
    0.78
    の
    0.72
    ные
    0.71
    ın
    0.69
    ን
    0.69
    :
    0.68
    ле
    0.68
    ла
    0.66
    ↵
    0.65
    Act Density 0.291%

    No Known Activations