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

    Neuronpedia

    INDEX
    Explanations

    promote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anı
    0.54
     cakkh
    0.52
     natomiast
    0.52
     ejecut
    0.52
     huidige
    0.52
    肦
    0.50
    轭
    0.50
     он
    0.48
    fi
    0.48
     sujeto
    0.48
    POSITIVE LOGITS
     headwinds
    0.48
    3
    0.47
    با
    0.47
    ความ
    0.46
     Walmart
    0.45
    بر
    0.45
    ما
    0.44
     market
    0.44
     beach
    0.44
    Tuesday
    0.44
    Act Density 0.000%

    No Known Activations