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

    Neuronpedia

    INDEX
    Explanations

    references to Wikipedia-related services and resources

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

    libraries and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.43
     Fakult
    -0.39
    resistant
    -0.37
     Burgess
    -0.37
     Bhattach
    -0.36
     Dör
    -0.35
     henvis
    -0.35
    糖
    -0.35
     Barbier
    -0.35
    "]:
    -0.35
    POSITIVE LOGITS
    évaluateur
    0.53
     الحره
    0.47
     CWE
    0.47
    CurrentValue
    0.46
     PeEnEo
    0.46
    rungsseite
    0.43
     lauter
    0.42
     RTI
    0.42
    Filmografia
    0.42
    󠁿
    0.42
    Act Density 0.031%

    No Known Activations