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

    Neuronpedia

    INDEX
    Explanations

    identifying main idea or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interpre
    0.43
    Converted
    0.43
     interpreta
    0.43
     ermöglichen
    0.42
    Downloading
    0.42
     جلسه
    0.41
     mevcut
    0.41
     quantifying
    0.41
     quantified
    0.41
    interpreted
    0.41
    POSITIVE LOGITS
     Think
    0.41
     amph
    0.40
     ast
    0.40
     아
    0.40
     হ
    0.39
     overthrow
    0.39
     rhymes
    0.39
     τρο
    0.39
     Ast
    0.38
     Vent
    0.38
    Act Density 0.002%

    No Known Activations