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

    Neuronpedia

    INDEX
    Explanations

    actually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     город
    -0.07
    .orange
    -0.07
     свого
    -0.07
    Clo
    -0.06
     vự
    -0.06
    ис
    -0.06
    ات
    -0.06
    .SE
    -0.06
    思い
    -0.06
    ونية
    -0.06
    POSITIVE LOGITS
     landscaping
    0.07
     moy
    0.06
     swingerclub
    0.06
     contamination
    0.06
     supported
    0.06
     bug
    0.06
     mound
    0.06
     MW
    0.06
    _community
    0.06
     Boone
    0.06
    Act Density 0.173%

    No Known Activations