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

    Neuronpedia

    INDEX
    Explanations

    states after conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethn
    0.69
     renewables
    0.67
    im
    0.66
    嘱
    0.64
    पक्ष
    0.63
    pe
    0.63
    í
    0.63
    সংস্কার
    0.62
    lem
    0.62
    array
    0.61
    POSITIVE LOGITS
     myös
    0.70
    ございます
    0.69
     있습니다
    0.69
     acestea
    0.69
     également
    0.68
     வகையில்
    0.68
     있어요
    0.67
     различни
    0.66
     것입니다
    0.65
     designado
    0.64
    Act Density 5.025%

    No Known Activations