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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     будет
    -0.08
     abundant
    -0.07
     Bridges
    -0.07
     Ning
    -0.07
    い
    -0.07
     nonetheless
    -0.07
    日晚
    -0.07
    いて
    -0.07
     mountain
    -0.07
     persever
    -0.06
    POSITIVE LOGITS
     dropped
    0.07
    XHR
    0.07
    诈
    0.07
     Obama
    0.07
    蝘
    0.07
    ﲰ
    0.07
    .loading
    0.07
    charges
    0.07
    役
    0.06
     Allocator
    0.06
    Act Density 0.013%

    No Known Activations