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
     fortunately
    -0.07
     blinds
    -0.07
     nearly
    -0.06
     результ
    -0.06
    nout
    -0.06
     eder
    -0.06
    ffect
    -0.06
    lerdir
    -0.06
    users
    -0.06
    rol
    -0.06
    POSITIVE LOGITS
     protestors
    0.07
    wię
    0.07
    YP
    0.07
    .ss
    0.07
    Repository
    0.06
     updatedAt
    0.06
    _FAMILY
    0.06
     ситуа
    0.06
    istica
    0.06
    ulty
    0.06
    Act Density 0.192%

    No Known Activations