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

    Neuronpedia

    INDEX
    Explanations

    mammals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াবণ
    0.78
     தமிழ்நாடு
    0.67
    ленный
    0.65
    ગત
    0.63
     блок
    0.62
     কর্মচারী
    0.61
    लापूर
    0.60
    ющий
    0.60
    затор
    0.59
    ौती
    0.58
    POSITIVE LOGITS
    backs
    1.76
    ixes
    1.76
    nows
    1.74
    olds
    1.70
    arks
    1.66
    ities
    1.64
    iums
    1.63
    ards
    1.63
    oids
    1.62
    offs
    1.62
    Act Density 2.296%

    No Known Activations