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

    Neuronpedia

    INDEX
    Explanations

    xmlns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NUM
    -0.07
    𨟠
    -0.07
    .Q
    -0.06
     décid
    -0.06
    Great
    -0.06
     Darwin
    -0.06
     представ
    -0.06
    越
    -0.06
    .pred
    -0.06
     optim
    -0.06
    POSITIVE LOGITS
    茅
    0.07
     Activation
    0.07
    ๋
    0.07
    Mvc
    0.07
     Deadly
    0.07
    icter
    0.07
    ░
    0.07
    流入
    0.07
    征收
    0.06
    .getAction
    0.06
    Act Density 0.033%

    No Known Activations