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

    Neuronpedia

    INDEX
    Explanations

    than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Others
    1.52
    Other
    1.49
     others
    1.49
     Other
    1.40
     otros
    1.38
     otras
    1.36
     Others
    1.34
     other
    1.34
    other
    1.32
     других
    1.31
    POSITIVE LOGITS
    worldly
    1.77
     than
    1.63
     equally
    1.59
     подобные
    1.59
    त्र
    1.56
     similar
    1.49
     niż
    1.49
     similarly
    1.47
    than
    1.42
     مشابه
    1.41
    Act Density 0.126%

    No Known Activations