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

    Neuronpedia

    INDEX
    Explanations

    documents, emails, and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -,
    -0.07
     oby
    -0.06
    (seconds
    -0.06
     objet
    -0.06
     buds
    -0.06
    Average
    -0.06
    ode
    -0.06
     signify
    -0.06
     ada
    -0.06
    -form
    -0.06
    POSITIVE LOGITS
     trimmed
    0.07
    Manip
    0.07
     vigorously
    0.07
     ApplicationException
    0.07
    ует
    0.06
    ENTRY
    0.06
    spě
    0.06
    ิษ
    0.06
    normalized
    0.06
     leaked
    0.06
    Act Density 0.015%

    No Known Activations