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

    Neuronpedia

    INDEX
    Explanations

    list markers and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     است
    0.23
     geben
    0.22
    ociaż
    0.21
    λικά
    0.20
     dés
    0.20
     poziomie
    0.20
    ',
    0.19
     punti
    0.19
     augmente
    0.19
     física
    0.19
    POSITIVE LOGITS
    +)
    0.19
    0.19
     Β
    0.18
     Ibid
    0.18
    )</
    0.17
     Greater
    0.17
     Mga
    0.17
     Majority
    0.17
    )/
    0.16
     Second
    0.16
    Act Density 0.633%

    No Known Activations