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

    Neuronpedia

    INDEX
    Explanations

    following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    osar
    1.60
     computerScore
    1.55
     basalt
    1.54
     rmse
    1.53
    мага
    1.52
     resell
    1.51
     csrf
    1.50
    verlet
    1.49
    armor
    1.49
    वत्ता
    1.48
    POSITIVE LOGITS
    いろいろ
    0.89
     Twe
    0.89
     Simpl
    0.89
     Several
    0.81
     calendário
    0.79
     ann
    0.76
     Accom
    0.74
     İn
    0.73
     plusieurs
    0.72
    延
    0.72
    Act Density 0.853%

    No Known Activations