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

    Neuronpedia

    INDEX
    Explanations

    forced march, water supply, fancy pot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଦ
    0.43
    quality
    0.42
    iderm
    0.41
    াচিত
    0.39
    complicated
    0.38
     Após
    0.38
     VOC
    0.37
     Este
    0.36
     Quality
    0.36
     Money
    0.36
    POSITIVE LOGITS
    宪
    0.39
     исти
    0.37
     پھیل
    0.36
    WithSize
    0.36
     பளி
    0.36
    쓱
    0.35
     þei
    0.35
     மொழ
    0.35
    xpath
    0.35
    ftÂ
    0.35
    Act Density 0.000%

    No Known Activations