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

    Neuronpedia

    INDEX
    Explanations

    Code and technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    또
    -0.07
    _orient
    -0.06
    .token
    -0.06
     yaşanan
    -0.06
     surround
    -0.06
    Ken
    -0.06
     nakonec
    -0.06
    ‌کن
    -0.06
     rightly
    -0.06
    ेखत
    -0.06
    POSITIVE LOGITS
     систем
    0.07
    Partial
    0.07
     duplicated
    0.07
    [result
    0.06
    161
    0.06
    party
    0.06
    .
    0.06
     decimal
    0.06
    (path
    0.06
    :white
    0.06
    Act Density 0.000%

    No Known Activations