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

    Neuronpedia

    INDEX
    Explanations

    dates and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    encerramento
    0.21
    ఎల్
    0.21
    யில்
    0.21
     serão
    0.21
     الفريق
    0.21
    equival
    0.21
    europe
    0.20
    솎
    0.20
    Hoch
    0.20
     printemps
    0.20
    POSITIVE LOGITS
     unused
    0.19
     निर्देशों
    0.19
     drog
    0.19
     dre
    0.18
     độ
    0.18
    ต
    0.18
    渗透
    0.17
     dane
    0.17
     shifter
    0.17
    दुर्
    0.17
    Act Density 0.005%

    No Known Activations