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

    Neuronpedia

    INDEX
    Explanations

    summarize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.12
    a
    -0.10
     unw
    -0.10
    ople
    -0.09
    TZ
    -0.09
    onn
    -0.09
     Trot
    -0.09
    ens
    -0.09
    -
    -0.09
    eder
    -0.08
    POSITIVE LOGITS
    izing
    0.22
    ize
    0.20
    ized
    0.18
    ization
    0.18
    ised
    0.14
    ising
    0.14
    izes
    0.13
    IZE
    0.13
    ily
    0.12
    izedName
    0.12
    Act Density 0.026%

    No Known Activations