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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "down" in various contexts

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

    "down" or "Down"

    np_acts-logits-general · gemini-2.0-flash

    down and associated concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.90
     betweenstory
    -0.88
    ształ
    -0.80
     itſelf
    -0.80
     themſelves
    -0.78
    PhysRev
    -0.76
     AssemblyCompany
    -0.76
     صوتيه
    -0.75
    ^(@)
    -0.75
     nahilalakip
    -0.73
    POSITIVE LOGITS
     Down
    0.99
    Down
    0.98
     down
    0.94
     DOWN
    0.93
    DOWN
    0.81
    Downs
    0.80
    down
    0.78
    downs
    0.77
    pour
    0.72
    dow
    0.72
    Act Density 0.127%

    No Known Activations