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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Space
    -0.08
    _bl
    -0.08
     blurred
    -0.08
     blending
    -0.08
    Table
    -0.08
    ाएँ
    -0.08
    ைகள
    -0.07
    .bl
    -0.07
    .Bl
    -0.07
     Pete
    -0.07
    POSITIVE LOGITS
     అంటే
    0.10
     refiere
    0.09
     నిర
    0.09
     bagian
    0.08
     చె
    0.08
     म्हणजे
    0.08
     એટલે
    0.07
     CPR
    0.07
     રાજ્ય
    0.07
     corde
    0.07
    Act Density 0.132%

    No Known Activations