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

    Neuronpedia

    INDEX
    Explanations

    Google Calendar API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    -1.27
    で
    -1.21
    を
    -1.18
    も
    -1.16
    ੧
    -1.13
     Certificado
    -1.11
    や
    -1.09
    ੨
    -1.07
    などの
    -1.06
     inad
    -1.06
    POSITIVE LOGITS
     restricted
    1.22
    なんですね
    1.20
     (
    1.15
    為に
    1.14
    Both
    1.13
     an
    1.09
    Different
    1.09
    場所で
    1.09
     &
    1.07
     being
    1.04
    Act Density 0.105%

    No Known Activations