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

    Neuronpedia

    INDEX
    Explanations

    words related to loss or absence

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

    gone or visible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.45
    bership
    -0.40
    chard
    -0.39
    chartInstance
    -0.39
    ckså
    -0.38
    wendigkeit
    -0.37
    \">\
    -0.37
    Abby
    -0.36
     ddelweddau
    -0.35
    Guard
    -0.35
    POSITIVE LOGITS
    GONE
    1.55
    Gone
    1.44
     Gone
    1.31
    gone
    1.11
    VISIBLE
    1.09
     GONE
    1.05
     gone
    0.69
     visible
    0.53
    visible
    0.52
    rungsseite
    0.52
    Act Density 0.001%

    No Known Activations