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

    Neuronpedia

    INDEX
    Explanations

    hiking, parks, picnics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mutating
    0.48
     meaningless
    0.48
     rewriting
    0.46
     impurity
    0.46
     supremacy
    0.46
     isomorphic
    0.45
     defam
    0.45
     superscript
    0.45
     atomically
    0.45
     rewrite
    0.44
    POSITIVE LOGITS
     Hiking
    1.01
     park
    1.00
    Hiking
    0.99
     hiking
    0.95
    公园
    0.94
     parks
    0.94
     Hike
    0.93
     hikes
    0.88
     picnic
    0.88
     parques
    0.88
    Act Density 0.064%

    No Known Activations