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

    Neuronpedia

    INDEX
    Explanations

    1.5 and 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simple
    -0.09
     सरल
    -0.08
     simples
    -0.08
    _simple
    -0.08
     links
    -0.08
     enl
    -0.08
    simple
    -0.08
     billboard
    -0.08
    (simple
    -0.07
     Simple
    -0.07
    POSITIVE LOGITS
    섭
    0.09
     Hopefully
    0.09
     assuntos
    0.09
     Jinping
    0.09
    功
    0.08
     последствия
    0.08
    毫
    0.08
     Humanity
    0.08
     உலக
    0.08
    世界
    0.08
    Act Density 0.002%

    No Known Activations