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

    Neuronpedia

    INDEX
    Explanations

    figures and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rité
    0.41
    ität
    0.39
    calo
    0.39
     bó
    0.39
    লিখিত
    0.38
     videos
    0.38
     concl
    0.37
    +".
    0.37
    扂
    0.37
    顎
    0.37
    POSITIVE LOGITS
     summarizing
    0.61
     summarizes
    0.57
     Table
    0.57
    Table
    0.54
     Figure
    0.52
    LayoutPanel
    0.50
    Figure
    0.50
    Fig
    0.49
     Fig
    0.49
     Figura
    0.48
    Act Density 0.009%

    No Known Activations