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

    Neuronpedia

    INDEX
    Explanations

    comments, user interactions, and indications of feedback or reviews

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

    URL shields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.88
     kasarigan
    -0.87
     &___
    -0.75
    Vidite
    -0.71
    httphttps
    -0.69
    tvguidetime
    -0.67
    enderror
    -0.66
    Билгалдахарш
    -0.65
    原始内容存档于
    -0.65
    AddTagHelper
    -0.65
    POSITIVE LOGITS
    Clik
    0.37
    🟤
    0.30
      
    0.29
    Â
    0.26
    arXiv
    0.26
    Unspecified
    0.26
    >*/
    0.26
    Externe
    0.26
     
    0.26
    AnchorStyles
    0.25
    Act Density 0.031%

    No Known Activations