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

    Neuronpedia

    INDEX
    Explanations

    items related to data collection and reporting within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stages or posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.68
    aarrggbb
    -0.67
    expandindo
    -0.54
     &___
    -0.54
    Fordítás
    -0.53
     للاسماء
    -0.50
    addCriterion
    -0.47
     ujednoznacz
    -0.47
     متحده
    -0.47
     podjet
    -0.47
    POSITIVE LOGITS
    
    0.48
     liên
    0.41
     te
    0.39
     stages
    0.39
     initial
    0.38
     progressively
    0.38
     staged
    0.38
    PostMapping
    0.37
     continu
    0.36
    GOTREF
    0.36
    Act Density 0.248%

    No Known Activations