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

    Neuronpedia

    INDEX
    Explanations

    Copyright, licensing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sp
    -0.07
     licence
    -0.07
    .Live
    -0.07
     liên
    -0.07
     uçuş
    -0.07
    ">×</
    -0.07
     Jog
    -0.06
    얻
    -0.06
    等领域
    -0.06
     rescued
    -0.06
    POSITIVE LOGITS
     Stark
    0.08
     Westminster
    0.07
     Baltimore
    0.07
    ক
    0.07
    _method
    0.07
     Ramirez
    0.07
     testers
    0.06
    initialize
    0.06
    \$
    0.06
    핫
    0.06
    Act Density 0.005%

    No Known Activations