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

    Neuronpedia

    INDEX
    Explanations

    event handling drug safety Bitemporal dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tekn
    0.52
    uros
    0.51
    tt
    0.46
    粝
    0.45
     Kontakt
    0.45
    zám
    0.45
    tes
    0.45
    na
    0.44
     Fiore
    0.44
    ducers
    0.44
    POSITIVE LOGITS
     ·
    0.48
    ']
    0.46
    )&=
    0.46
     בס
    0.46
     גר
    0.45
    ༈
    0.45
     emit
    0.44
    म्मी
    0.44
    անկ
    0.44
    )\\
    0.43
    Act Density 0.001%

    No Known Activations