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

    Neuronpedia

    INDEX
    Explanations

    has taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     строка
    0.59
     đề
    0.55
     линии
    0.54
     incluidas
    0.54
    <0x07>
    0.53
     trước
    0.52
     adecuadas
    0.51
    को
    0.51
    tı
    0.51
     বয়ে
    0.51
    POSITIVE LOGITS
     Intensive
    0.50
    紜
    0.48
    ching
    0.47
     Biological
    0.47
     ressort
    0.46
    antum
    0.45
    ardom
    0.45
     raref
    0.45
    ى
    0.44
    uttam
    0.44
    Act Density 0.000%

    No Known Activations