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

    Neuronpedia

    INDEX
    Explanations

    portal device

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    让他们
    0.48
    恋爱
    0.48
    ᱠ
    0.47
    この
    0.46
    På
    0.46
     crescimento
    0.45
    údo
    0.45
    悝
    0.45
     discurso
    0.45
    Unless
    0.44
    POSITIVE LOGITS
    yml
    0.46
     StringSet
    0.46
     strap
    0.46
     regl
    0.44
     Eurasia
    0.43
     float
    0.43
     selector
    0.43
     cord
    0.42
    arity
    0.42
     หล
    0.42
    Act Density 0.001%

    No Known Activations