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

    Neuronpedia

    INDEX
    Explanations

    references to television or TV-related devices

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

    TV receiver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cohen
    -0.37
     new
    -0.36
     ge
    -0.34
     shaped
    -0.33
    eda
    -0.33
     A
    -0.33
     '
    -0.32
    .
    -0.32
    endes
    -0.32
     [
    -0.32
    POSITIVE LOGITS
     televisor
    1.00
     TVs
    0.96
     <<<<<<<<<<<<<<
    0.95
     televisions
    0.94
     televiz
    0.88
    帖最后由
    0.83
    ंदीखरीदारी
    0.82
    Television
    0.82
     Tv
    0.80
     Television
    0.79
    Act Density 0.009%

    No Known Activations