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

    Neuronpedia

    INDEX
    Explanations

    backbone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     risking
    -0.07
     Miz
    -0.07
     更新
    -0.07
    がお
    -0.06
     "@
    -0.06
     Dec
    -0.06
     هنگام
    -0.06
    .currentIndex
    -0.06
    ')->
    -0.06
    еріг
    -0.06
    POSITIVE LOGITS
     backbone
    0.16
     spine
    0.10
     Backbone
    0.09
    -backed
    0.08
     back
    0.08
    bone
    0.08
    onomy
    0.08
    (pow
    0.08
     sağlam
    0.07
    ované
    0.07
    Act Density 0.002%

    No Known Activations