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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns, particularly names and titles

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

    Wilbur Ross, Messalina wait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SSH
    -0.41
    ambassade
    -0.40
     ascorbic
    -0.39
    Zig
    -0.37
     Alhambra
    -0.37
     inom
    -0.36
    IconButton
    -0.36
     Bolshe
    -0.36
     Wolverine
    -0.36
     Numerade
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.55
     jPanel
    0.53
    endpush
    0.51
    SpringBootTest
    0.51
    tagHelperRunner
    0.50
     ब्रेकडाउन
    0.48
    niająca
    0.47
    Obrázky
    0.46
    MENAFN
    0.46
     unknownFields
    0.45
    Act Density 0.109%

    No Known Activations