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

    Neuronpedia

    INDEX
    Explanations

    servers categorized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     morphism
    0.66
     Components
    0.66
     components
    0.65
     détermine
    0.64
    components
    0.64
     определяет
    0.64
    вым
    0.63
     davran
    0.62
    Components
    0.62
     systeem
    0.62
    POSITIVE LOGITS
     categorized
    1.38
     suitable
    1.15
     galore
    1.13
     tagged
    1.12
     listed
    1.11
     sorted
    1.10
     worth
    1.05
     available
    1.04
     featuring
    1.03
     ranked
    1.01
    Act Density 0.484%

    No Known Activations