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

    Neuronpedia

    INDEX
    Explanations

    HTML SVG

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BOA
    0.52
     NSA
    0.49
    Zara
    0.45
    CoA
    0.44
    CAA
    0.44
    ASA
    0.43
     ECA
    0.43
    NSA
    0.42
     CASA
    0.42
     ASA
    0.41
    POSITIVE LOGITS
     وده
    0.45
    ране
    0.44
     Brend
    0.42
     Độ
    0.40
     તમે
    0.40
     মার্কে
    0.40
     Sloven
    0.39
    indrome
    0.39
    CCE
    0.39
    pare
    0.38
    Act Density 0.002%

    No Known Activations