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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizational units or divisions

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

    unit and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Públicas
    -0.45
     picioare
    -0.42
     argint
    -0.40
     Paglinawan
    -0.40
     acoper
    -0.40
    ELESS
    -0.39
    Geographie
    -0.38
    ktır
    -0.37
    ală
    -0.37
    phemy
    -0.36
    POSITIVE LOGITS
     Unit
    1.75
    Unit
    1.59
     unit
    1.52
     UNIT
    1.39
    unit
    1.29
     Units
    1.23
    UNIT
    1.23
     units
    1.09
    Units
    0.99
    ユニット
    0.97
    Act Density 0.014%

    No Known Activations