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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artisan
    -0.07
     spree
    -0.07
    Thunder
    -0.07
    중앙
    -0.07
     themed
    -0.07
    .cljs
    -0.07
    argo
    -0.07
    哈利
    -0.07
    Mari
    -0.07
    dü
    -0.07
    POSITIVE LOGITS
    °F
    0.07
    _PAD
    0.07
    夼
    0.07
     kwargs
    0.07
    xed
    0.06
     assures
    0.06
    呖
    0.06
    ,len
    0.06
     offs
    0.06
    _EP
    0.06
    Act Density 0.014%

    No Known Activations