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

    Neuronpedia

    INDEX
    Explanations

    whose or with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    this
    0.54
     acestea
    0.49
     jų
    0.46
    Avro
    0.46
    เป็น
    0.46
    ເປັນ
    0.46
     these
    0.46
     themselves
    0.45
    ίναι
    0.45
     이는
    0.44
    POSITIVE LOGITS
     cuya
    0.66
     Whose
    0.66
     whose
    0.64
     जिसने
    0.57
     cuyas
    0.57
     capable
    0.56
     cuyo
    0.56
     prone
    0.52
     cujo
    0.51
     cuyos
    0.50
    Act Density 0.133%

    No Known Activations