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

    Neuronpedia

    INDEX
    Explanations

    exceptions and special cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    崱
    0.50
    Plugins
    0.48
    琿
    0.48
     হবে
    0.46
    ২৬
    0.45
    パス
    0.44
    伈
    0.44
    サービス
    0.43
     повинні
    0.43
    ୌ
    0.43
    POSITIVE LOGITS
     Alzheimer
    0.46
     Exceptions
    0.44
     lact
    0.44
     arterioles
    0.43
     exceptionnelle
    0.43
     Except
    0.42
     antihist
    0.41
     alcoholic
    0.41
     threshold
    0.40
     exceptions
    0.40
    Act Density 0.007%

    No Known Activations