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

    Neuronpedia

    INDEX
    Explanations

    heritage science conservation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.88
    í
    0.84
    ion
    0.82
    IT
    0.76
     visión
    0.75
    LET
    0.74
    기
    0.71
    an
    0.68
    OP
    0.67
    ática
    0.67
    POSITIVE LOGITS
    amı
    1.07
     Heritage
    0.95
     heritage
    0.93
    ۰
    0.93
    ir
    0.91
    শালী
    0.88
    ד
    0.88
    ৭
    0.87
     in
    0.85
    nq
    0.81
    Act Density 0.001%

    No Known Activations