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

    Neuronpedia

    INDEX
    Explanations

    Algorithms and Braves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pdf
    0.30
    PDF
    0.30
    农业
    0.29
    Overview
    0.29
    Type
    0.28
    Facing
    0.28
    Mango
    0.28
    洋
    0.27
    Machine
    0.27
    Context
    0.27
    POSITIVE LOGITS
     ganz
    0.34
     personnages
    0.34
    žky
    0.33
     मुझे
    0.32
     반
    0.32
     sayings
    0.32
     quartiers
    0.31
     những
    0.31
     المراجعه
    0.31
     내가
    0.31
    Act Density 0.000%

    No Known Activations