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

    Neuronpedia

    INDEX
    Explanations

    risk of portfolios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    models
    0.52
     sulfuric
    0.49
    asteroid
    0.48
     rhino
    0.46
    calculate
    0.46
     calculated
    0.45
     sedimentary
    0.45
    keys
    0.45
    এরপর
    0.45
    ڈی
    0.44
    POSITIVE LOGITS
    ↵
    0.52
    並
    0.46
     daarbij
    0.45
     സ്ഥി
    0.44
     Oz
    0.43
     appre
    0.43
     Voll
    0.42
     portfolios
    0.41
     getroffen
    0.41
    jé
    0.41
    Act Density 0.003%

    No Known Activations