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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "explain" and its variations, indicating a focus on clarification or description of details

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

    explaining with that, how, why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roost
    -0.57
     Rooster
    -0.56
     mergeFrom
    -0.52
     BoxFit
    -0.50
     bankası
    -0.49
    accumulative
    -0.49
     bookmark
    -0.49
    Bong
    -0.48
     Bomber
    -0.48
     Barley
    -0.48
    POSITIVE LOGITS
     explained
    0.80
     explain
    0.74
     explaining
    0.61
     explanation
    0.60
     Explained
    0.59
    explain
    0.58
     Explain
    0.57
     expliqué
    0.57
     expliquer
    0.56
    explained
    0.56
    Act Density 0.015%

    No Known Activations