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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mass
    0.71
    mass
    0.62
     массо
    0.55
     Mass
    0.55
     masa
    0.53
    Mass
    0.51
    MASS
    0.48
     massa
    0.46
     масса
    0.45
     MASS
    0.42
    POSITIVE LOGITS
    TERMIN
    0.40
    enroll
    0.37
     עוד
    0.37
    ϒ
    0.37
    ライン
    0.36
    डाय
    0.36
     vâ
    0.35
    𝓉
    0.35
    Italy
    0.35
     इस्लाम
    0.34
    Act Density 0.000%

    No Known Activations