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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기자
    -0.07
     its
    -0.07
     ITS
    -0.07
     honoring
    -0.07
     jerk
    -0.06
    .LogError
    -0.06
     Witch
    -0.06
     bathrooms
    -0.06
     Gorgeous
    -0.06
    kle
    -0.06
    POSITIVE LOGITS
     #:
    0.06
    ATABASE
    0.06
     mip
    0.06
     Scalar
    0.06
    setName
    0.06
    елич
    0.06
    pointer
    0.06
    aru
    0.06
    ={[
    0.06
     Maduro
    0.06
    Act Density 0.004%

    No Known Activations