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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Paths
    -0.07
    <td
    -0.06
    -0.06
     kayn
    -0.06
    mos
    -0.06
    separator
    -0.06
     obey
    -0.06
    ために
    -0.06
    _characters
    -0.06
    Nevertheless
    -0.05
    POSITIVE LOGITS
    ös
    0.07
     stre
    0.07
    推薦
    0.06
     succeeds
    0.06
     predic
    0.06
    (existing
    0.06
    %;
    0.06
    uckets
    0.06
     을
    0.06
     Plains
    0.06
    Act Density 0.049%

    No Known Activations