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

    Neuronpedia

    INDEX
    Explanations

    historical trauma topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    0.50
    га
    0.46
    Arr
    0.43
    徃
    0.42
    म
    0.41
    ப
    0.40
    бор
    0.39
    いろいろ
    0.39
    很大的
    0.39
    мене
    0.38
    POSITIVE LOGITS
     ONLY
    0.46
     FIX
    0.46
     THIS
    0.45
     Collect
    0.45
     Translations
    0.45
     Fairfax
    0.44
     Compatibility
    0.44
     Refunds
    0.44
     Charming
    0.43
     Only
    0.43
    Act Density 0.001%

    No Known Activations