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

    Neuronpedia

    INDEX
    Explanations

    words starting with "Cor"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estamp
    0.44
    اہم
    0.42
    ამო
    0.40
    感觉
    0.39
    OHAMA
    0.38
     заниматься
    0.38
    都道府県
    0.38
     imitated
    0.37
    ędzynarod
    0.37
    ا
    0.37
    POSITIVE LOGITS
    Cor
    1.28
     Cor
    1.18
     cor
    1.13
    cor
    1.11
     COR
    1.00
     kor
    0.97
    COR
    0.95
     кор
    0.90
     Kor
    0.89
     Corv
    0.81
    Act Density 0.012%

    No Known Activations