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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating regulatory compliance and associated risks in various industries

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

    medical/critical applications importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.51
    findpost
    -0.46
     lenker
    -0.46
     mergeFrom
    -0.46
     للمعارف
    -0.45
     вікісторінку
    -0.45
     تضيفلها
    -0.44
    rungsseite
    -0.41
    CodedInputStream
    -0.41
    httphttps
    -0.41
    POSITIVE LOGITS
     beroep
    0.42
     accuracy
    0.40
     North
    0.40
    Accuracy
    0.37
     Public
    0.37
    ceng
    0.37
     Accuracy
    0.36
     critical
    0.36
     Math
    0.36
    wantErr
    0.35
    Act Density 0.088%

    No Known Activations