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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ra
    2.38
    에
    2.17
    ist
    2.14
    ik
    2.03
    rh
    1.96
    ра
    1.94
    కు
    1.93
    rz
    1.92
    lığ
    1.91
    に
    1.84
    POSITIVE LOGITS
    い
    2.34
     fleste
    2.33
    ਰ
    2.20
     amelyek
    2.13
     principales
    2.05
    வற்றை
    2.02
     kurie
    2.02
    ीय
    2.00
     habilidades
    1.96
    jų
    1.94
    Act Density 0.217%

    No Known Activations