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

    Neuronpedia

    INDEX
    Explanations

    specific names and entities, particularly those related to individuals or organizations

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

    Follows a two or three letter sequence ending in "k"

    np_acts-logits-general · gemini-2.0-flash

    ending in -ak, -ack, -ek, -ink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getItemId
    -0.48
    RefNanny
    -0.48
    æder
    -0.46
     Mathieu
    -0.45
     Harrison
    -0.44
    aini
    -0.44
    ällor
    -0.43
     Dove
    -0.43
    GeV
    -0.42
    Mathieu
    -0.42
    POSITIVE LOGITS
     DAK
    0.98
     SAK
    0.98
    pck
    0.97
     Hek
    0.96
     MCK
    0.95
    RAK
    0.95
     Shak
    0.94
     PAK
    0.94
    Bk
    0.93
    ARK
    0.93
    Act Density 0.756%

    No Known Activations