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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seem
    -0.07
    💟
    -0.07
     despair
    -0.07
    썽
    -0.07
     Monterey
    -0.07
     Georgetown
    -0.07
     Leigh
    -0.06
    (project
    -0.06
     assort
    -0.06
    ӣ
    -0.06
    POSITIVE LOGITS
    无声
    0.07
    ]:↵↵↵
    0.07
    иру
    0.07
    軟
    0.07
     bonus
    0.07
    \"",↵
    0.07
     Barth
    0.07
    ld
    0.07
    flare
    0.07
     мяг
    0.07
    Act Density 0.017%

    No Known Activations