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

    Neuronpedia

    INDEX
    Explanations

    namely, Arabic, Hindi, Bengali

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     them
    0.29
     me
    0.29
    -
    0.28
     him
    0.27
     open
    0.26
    S
    0.26
     in
    0.25
     a
    0.25
     mo
    0.25
     by
    0.25
    POSITIVE LOGITS
     Namely
    0.40
    mataspid
    0.31
    namely
    0.29
     Nucleaire
    0.29
     nitidus
    0.28
    ಿಸಲಾಗಿದೆ
    0.28
     angulis
    0.27
     চিকিৎ
    0.27
     अर्थात्
    0.27
    襬
    0.27
    Act Density 0.000%

    No Known Activations