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

    Neuronpedia

    INDEX
    Explanations

    provide search keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     കാര്യ
    0.50
    BV
    0.48
    ",
    0.47
    Constraint
    0.46
     reunión
    0.46
     प्रतिभाशाली
    0.45
     बीज
    0.44
     ውሃ
    0.44
    >",
    0.44
    ão
    0.44
    POSITIVE LOGITS
     exerc
    0.46
    odan
    0.44
    介
    0.43
     freshly
    0.43
    ਨ
    0.43
    素
    0.42
     indign
    0.41
     opulent
    0.41
    练习
    0.41
    ’
    0.41
    Act Density 0.002%

    No Known Activations