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

    Neuronpedia

    INDEX
    Explanations

    around bios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aunt
    0.52
     flatness
    0.50
     effic
    0.49
     መጠን
    0.49
     lao
    0.49
     allege
    0.49
     haste
    0.47
     autre
    0.47
     devise
    0.46
     flash
    0.46
    POSITIVE LOGITS
    ები
    0.46
    ља
    0.43
    ieniem
    0.43
    ā
    0.43
    ারিত
    0.42
    Сред
    0.42
    appears
    0.42
    мента
    0.42
    aría
    0.42
    andus
    0.42
    Act Density 0.001%

    No Known Activations