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

    Neuronpedia

    INDEX
    Explanations

    recurriendo, escribiera, establecen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comer
    0.60
     extrapolation
    0.53
     proponent
    0.53
     daunting
    0.52
     derogatory
    0.52
     misconception
    0.52
     extrapol
    0.51
     conducive
    0.51
     imperative
    0.51
     acronym
    0.50
    POSITIVE LOGITS
    issaient
    0.53
    in
    0.51
    uje
    0.49
    entesque
    0.49
    а
    0.49
    ються
    0.48
    ercise
    0.47
    able
    0.47
     Новости
    0.47
    ando
    0.47
    Act Density 0.157%

    No Known Activations