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

    Neuronpedia

    INDEX
    Explanations

    home features and amenities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baths
    0.46
    ಯಲ್ಲಿ
    0.41
     catamaran
    0.40
     usable
    0.39
    内に
    0.39
    jsonObject
    0.39
     Bath
    0.39
    bath
    0.38
     immaculate
    0.38
     habitable
    0.37
    POSITIVE LOGITS
     enhances
    0.46
     system
    0.41
     alleviate
    0.41
     promotes
    0.40
     ensures
    0.40
     regain
    0.39
     diminishes
    0.39
     helps
    0.39
     nearing
    0.39
     anticipates
    0.39
    Act Density 0.001%

    No Known Activations