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

    Neuronpedia

    INDEX
    Explanations

    information regarding unresolved issues and delays in processes

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

    Delays, inaction, and waiting

    np_acts-logits-general · gemini-2.0-flash

    delays and inaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reverse
    -0.43
    Short
    -0.42
    DBS
    -0.41
     Sing
    -0.41
     Short
    -0.41
     Pote
    -0.40
    Reverse
    -0.40
     Reverse
    -0.40
    wijk
    -0.40
    pluck
    -0.40
    POSITIVE LOGITS
     delay
    0.70
     delays
    0.69
     delaying
    0.59
     retraso
    0.56
     inaction
    0.54
    -------------</
    0.54
     مشين
    0.52
     delayed
    0.52
     Delays
    0.51
     inactivity
    0.49
    Act Density 0.349%

    No Known Activations