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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions, lists, conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    0.48
    ปลี่ยน
    0.47
    德
    0.47
    랜드
    0.46
     монта
    0.45
     जाणून
    0.45
     확인함
    0.45
    รถ
    0.44
     اعمال
    0.44
    ᱛ
    0.44
    POSITIVE LOGITS
    ní
    0.48
    im
    0.48
    is
    0.46
     pubs
    0.44
    vm
    0.44
    as
    0.43
    },
    0.43
    óm
    0.43
    wert
    0.43
    ဟုတ်
    0.43
    Act Density 0.002%

    No Known Activations