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

    Neuronpedia

    INDEX
    Explanations

    high numerical values related to conditions or guidelines

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

    non-english technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ditemp
    -0.35
    voegen
    -0.34
     merve
    -0.34
     φω
    -0.33
     aydın
    -0.32
     vē
    -0.32
    -0.32
    }\
    -0.32
    extré
    -0.31
     Deckel
    -0.31
    POSITIVE LOGITS
    الحياه
    0.89
    rungsseite
    0.71
    matchCondition
    0.66
    Diwedd
    0.65
     FetchType
    0.65
    ########.
    0.64
    httphttps
    0.64
     tartalomajánló
    0.61
    SourceChecksum
    0.60
     esternos
    0.60
    Act Density 0.001%
    No Known Activations