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

    Neuronpedia

    INDEX
    Explanations

    descriptive states and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     account
    0.49
     equipment
    0.49
     accounts
    0.49
     chunks
    0.46
     scaffolds
    0.46
     receptors
    0.46
     generators
    0.45
     hives
    0.45
     daff
    0.45
     injuries
    0.44
    POSITIVE LOGITS
    Geometry
    0.50
    継続
    0.49
    Geometric
    0.48
    Ш
    0.47
    W
    0.47
    1
    0.46
    Behavior
    0.44
    هَا
    0.44
    ?»
    0.44
    ()'
    0.44
    Act Density 0.010%

    No Known Activations