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

    Neuronpedia

    INDEX
    Explanations

    html document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    albumin
    0.67
     обознача
    0.65
     habitaciones
    0.59
     albumin
    0.58
    imethyl
    0.58
    atoti
    0.57
     ডো
    0.56
     válv
    0.56
     озера
    0.56
     cisplatin
    0.56
    POSITIVE LOGITS
    ##
    0.47
     ##
    0.41
    //
    0.40
     ছ
    0.40
     ####
    0.39
     каз
    0.39
     。,
    0.39
    ढे
    0.39
     very
    0.39
     дуже
    0.38
    Act Density 0.021%

    No Known Activations