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

    Neuronpedia

    INDEX
    Explanations

    referring to you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dla
    1.07
    Für
    0.91
    Для
    0.91
     für
    0.90
     for
    0.85
    For
    0.84
     для
    0.83
    共に
    0.81
    Untuk
    0.81
     voor
    0.80
    POSITIVE LOGITS
     personally
    1.24
     pribadi
    0.92
    zit
    0.91
     Personally
    0.90
     (;
    0.88
    而言
    0.87
     개인
    0.85
    来说
    0.83
     contingent
    0.83
     лично
    0.82
    Act Density 0.032%

    No Known Activations