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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ạ
    0.33
     ശേഖ
    0.33
     ചരി
    0.32
     पुल्लिंग
    0.30
     regione
    0.30
     defini
    0.28
     ภาพ
    0.28
     Fleurit
    0.28
     التعريف
    0.28
     iniz
    0.28
    POSITIVE LOGITS
    yn
    0.37
    ing
    0.33
     livestock
    0.31
    льные
    0.30
    OGA
    0.30
    7
    0.30
    ong
    0.29
    ager
    0.29
    /
    0.29
    4
    0.29
    Act Density 0.048%

    No Known Activations