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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .eql
    -0.07
    .After
    -0.06
     PDF
    -0.06
    .Calendar
    -0.06
     sample
    -0.06
     roller
    -0.06
     catalyst
    -0.06
     ErrorMessage
    -0.06
     nl
    -0.06
     After
    -0.06
    POSITIVE LOGITS
    ervised
    0.08
    tahun
    0.07
    EX
    0.07
    Grupo
    0.06
     типа
    0.06
    тів
    0.06
    plant
    0.06
    Renderer
    0.06
    -м
    0.06
    REAT
    0.06
    Act Density 0.013%

    No Known Activations