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

    Neuronpedia

    INDEX
    Explanations

    book club

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    0.62
     choreographer
    0.55
    Field
    0.50
     priest
    0.50
     field
    0.48
     Field
    0.48
     photographer
    0.48
     thumbnail
    0.48
    ა
    0.47
    เขียน
    0.47
    POSITIVE LOGITS
     EVs
    0.58
    ⦖
    0.58
     activités
    0.57
     endroits
    0.56
    circled
    0.56
     основним
    0.55
     ordinaire
    0.54
    取り組み
    0.54
     остан
    0.54
    瞔
    0.54
    Act Density 0.001%

    No Known Activations