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

    Neuronpedia

    INDEX
    Explanations

    Rust derive attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polluted
    0.45
    RELATIVA
    0.45
    襞
    0.45
     प्रदू
    0.41
    LEGISLATIVE
    0.40
    Ⴌ
    0.40
    ocre
    0.39
    蠵
    0.39
     VENT
    0.39
    ermis
    0.38
    POSITIVE LOGITS
     Clone
    1.02
    Clone
    0.97
     Copy
    0.80
     clone
    0.75
    Copy
    0.75
    Debug
    0.71
     Debug
    0.71
     PartialEq
    0.70
    clone
    0.68
     copy
    0.67
    Act Density 0.006%

    No Known Activations