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

    Neuronpedia

    INDEX
    Explanations

    Vector, geometry, advertising, letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ּוֹ
    -2.03
     if
    -1.64
    ַּ
    -1.59
    ִּ
    -1.48
    וּ
    -1.42
    ֶּ
    -1.41
     by
    -1.32
     service
    -1.31
    ְּ
    -1.31
     napisa
    -1.30
    POSITIVE LOGITS
    ׇ
    1.77
     מים
    1.66
    还
    1.36
    цький
    1.35
    ㄹ
    1.33
    meleri
    1.32
     แต่
    1.32
    Ку
    1.30
    ֳ
    1.29
     religieux
    1.28
    Act Density 0.021%

    No Known Activations