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

    Neuronpedia

    INDEX
    Explanations

    published RFCs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marketing
    0.48
     purchasing
    0.46
     producto
    0.46
     Royal
    0.46
     Alb
    0.46
     Licensed
    0.46
     Sheet
    0.46
     Caribbean
    0.45
     Playa
    0.45
     Exterior
    0.45
    POSITIVE LOGITS
     участи
    0.52
     murderous
    0.51
     হত্যাকা
    0.50
    uvwxyz
    0.49
    äller
    0.48
     thwarted
    0.46
     pthread
    0.46
     மொத்தம்
    0.45
    렬
    0.45
     নৃশংস
    0.44
    Act Density 0.002%

    No Known Activations