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

    Neuronpedia

    INDEX
    Explanations

    words related to assistance and support

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

    following "help" or "helps"

    np_acts-logits-general · gemini-2.0-flash

    acts of helping understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.60
    be
    -0.58
    use
    -0.55
    🎳
    -0.54
     soient
    -0.53
    timeScale
    -0.52
    Personensuche
    -0.52
     للمعارف
    -0.51
     capaz
    -0.51
    saraba
    -0.51
    POSITIVE LOGITS
    fully
    0.90
     solve
    0.82
     facilitate
    0.75
     improve
    0.74
     strengthen
    0.72
     alleviate
    0.71
    desk
    0.71
     propOrder
    0.71
     ensure
    0.69
     protect
    0.67
    Act Density 0.056%

    No Known Activations