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

    Neuronpedia

    INDEX
    Explanations

    explaining ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.48
    3
    0.43
    کو
    0.40
    ুগত্য
    0.39
     complacency
    0.39
     hobbies
    0.38
    런
    0.37
     πάν
    0.37
     spindles
    0.36
    1
    0.35
    POSITIVE LOGITS
    an
    0.68
    t
    0.66
    ان
    0.61
    ت
    0.59
    r
    0.57
    त
    0.57
    ת
    0.57
    ah
    0.56
    ر
    0.55
    ي
    0.55
    Act Density 0.345%

    No Known Activations