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

    Neuronpedia

    INDEX
    Explanations

    functions defining equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veröffent
    0.90
    いたしました
    0.89
     terceros
    0.87
     Ulster
    0.86
    tiered
    0.83
     silahkan
    0.82
    遊
    0.82
    τουργ
    0.80
    ほか
    0.80
     Raffa
    0.79
    POSITIVE LOGITS
     asymptotically
    1.40
     monotonically
    1.20
     perturbed
    1.10
     computed
    1.09
     perturb
    1.07
     encodes
    1.07
     satisfying
    1.06
     induced
    1.06
     cancel
    1.05
     satisfied
    1.04
    Act Density 0.793%

    No Known Activations