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

    Neuronpedia

    INDEX
    Explanations

    hidden, messy, crazy, sick, hero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    格
    0.47
    絖
    0.46
    ুদ্ধে
    0.45
    algebras
    0.45
     académica
    0.45
    ，
    0.43
     impress
    0.43
     রেক
    0.43
    是对
    0.43
     mathematicians
    0.42
    POSITIVE LOGITS
     Hidden
    0.44
    abinieri
    0.44
    Hidden
    0.43
    ާތ
    0.42
    lol
    0.42
     सबकुछ
    0.42
    Details
    0.42
    cock
    0.41
     הי
    0.41
    çamento
    0.41
    Act Density 0.004%

    No Known Activations