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

    Neuronpedia

    INDEX
    Explanations

    terms related to progress or advancements in various fields

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

    advancing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rotum
    -0.41
     Szk
    -0.38
    irchen
    -0.36
    kamer
    -0.36
    Museums
    -0.35
     roomId
    -0.35
    kg
    -0.35
     oreja
    -0.34
     coisa
    -0.34
    roomId
    -0.33
    POSITIVE LOGITS
     Advance
    1.19
    Advance
    1.13
     advance
    1.12
     ADVANCE
    1.09
     advances
    1.09
    advance
    1.07
     Advances
    0.97
     advancement
    0.96
    vancing
    0.94
     advancing
    0.93
    Act Density 0.011%

    No Known Activations