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

    Neuronpedia

    INDEX
    Explanations

    references to honey and related terms

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

    honeycomb, honeymoon, honey mead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cale
    -0.47
    bua
    -0.46
    typeorm
    -0.45
    Vegeta
    -0.43
    部
    -0.42
     Passat
    -0.42
     Parke
    -0.41
    ╡
    -0.40
    tsburgh
    -0.40
    卒
    -0.40
    POSITIVE LOGITS
     Honey
    1.21
    Honey
    1.20
    honey
    1.16
     honey
    1.13
     HONEY
    1.07
     honeymoon
    0.81
     Honig
    0.79
     Honeywell
    0.73
     Honeymoon
    0.73
     honeycomb
    0.72
    Act Density 0.005%

    No Known Activations