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

    Neuronpedia

    INDEX
    Explanations

    age-related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹏
    0.42
    ולוג
    0.41
    ärg
    0.39
    its
    0.38
     them
    0.38
    ogy
    0.38
    ///
    0.38
     राम
    0.38
    adik
    0.37
    чать
    0.37
    POSITIVE LOGITS
    Age
    0.49
     age
    0.48
     возрасте
    0.47
     Avec
    0.45
     Age
    0.44
     With
    0.43
    റായി
    0.43
    Tangent
    0.43
     vâr
    0.43
    With
    0.42
    Act Density 0.000%

    No Known Activations