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

    Neuronpedia

    INDEX
    Explanations

    references to fields related to data retrieval or programming methods

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

    technical method names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.82
    .*")]
    -0.74
    transQ
    -0.64
     Biôgrafia
    -0.56
     Wikimedijinoj
    -0.55
    parsedMessage
    -0.54
    JoinTable
    -0.52
    GEBURTSDATUM
    -0.52
    ſammen
    -0.51
    蚪
    -0.51
    POSITIVE LOGITS
    こちらも
    0.38
    同じく
    0.38
     Nacionales
    0.35
     ejus
    0.33
     يتيمه
    0.32
     ebenfalls
    0.31
     likewise
    0.31
    AndroidJUnit
    0.31
     sorella
    0.31
    WriteAttribute
    0.30
    Act Density 0.000%

    No Known Activations