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

    Neuronpedia

    INDEX
    Explanations

    people in roles and relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exploded
    0.31
    0.30
    text
    0.30
     x
    0.30
    label
    0.29
     &=
    0.29
     was
    0.28
     bytes
    0.28
     ');
    0.28
     used
    0.28
    POSITIVE LOGITS
     ktorí
    0.53
     quienes
    0.49
     who
    0.47
     quien
    0.44
     którzy
    0.43
     الذين
    0.42
     whom
    0.41
    에게
    0.39
     kteří
    0.38
     जिन्होंने
    0.38
    Act Density 1.149%

    No Known Activations