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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ForeColor
    -0.07
    li
    -0.07
     status
    -0.06
    	include
    -0.06
    力量
    -0.06
    AMED
    -0.06
     invalid
    -0.06
    drawer
    -0.06
     Updating
    -0.06
     assignments
    -0.06
    POSITIVE LOGITS
    問
    0.07
    atten
    0.07
    ogne
    0.06
    нул
    0.06
    .Authentication
    0.06
     intestinal
    0.06
    _GC
    0.06
    аль
    0.06
     acquaintance
    0.06
     Eric
    0.06
    Act Density 0.003%

    No Known Activations