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

    Neuronpedia

    INDEX
    Explanations

    looking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आधारित
    1.31
    ansive
    1.22
    bicara
    1.15
    存在する
    1.14
    centric
    1.14
    based
    1.12
    embangkan
    1.12
     orientated
    1.12
     기반
    1.12
    abhavam
    1.11
    POSITIVE LOGITS
     s
    0.84
     一
    0.84
     y
    0.83
     -
    0.79
     –
    0.79
     is
    0.77
     er
    0.77
    0.75
     not
    0.74
     n
    0.74
    Act Density 0.052%

    No Known Activations