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

    Neuronpedia

    INDEX
    Explanations

    Discourse markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harrison
    -0.08
    ߙ
    -0.08
     Resume
    -0.07
     Darling
    -0.07
    .sidebar
    -0.07
    _Login
    -0.07
    程序员
    -0.07
    _alarm
    -0.07
    Disposed
    -0.07
     Reid
    -0.07
    POSITIVE LOGITS
     Spa
    0.07
    Space
    0.07
    𝐟
    0.06
    table
    0.06
    Ă
    0.06
    }',↵
    0.06
     связи
    0.06
     verbs
    0.06
    >S
    0.06
    func
    0.06
    Act Density 0.114%

    No Known Activations