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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles related to stories or literary works

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

    fairy tales and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HostException
    -0.58
    GOTREF
    -0.56
    Jeografia
    -0.53
     disambiguazione
    -0.51
     mergeFrom
    -0.51
    وفاته
    -0.50
    Tikang
    -0.50
    olescence
    -0.49
    ंदीखरीदारी
    -0.49
    المكان
    -0.49
    POSITIVE LOGITS
     dwarfs
    0.49
     hunts
    0.44
     dwarf
    0.43
     dwar
    0.42
     Dwar
    0.40
     Snow
    0.39
    twimg
    0.38
     Dwarf
    0.38
     '\\;'
    0.37
    getDoctrine
    0.36
    Act Density 0.006%

    No Known Activations