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

    Neuronpedia

    INDEX
    Explanations

    certain phrases related to travel activities and locations

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

    Follows certain punctuation or sentence starts

    np_acts-logits-general · gemini-2.0-flash

    temporal sequencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -1.01
     lenker
    -0.95
     autorytatywna
    -0.79
     مشين
    -0.77
    Personensuche
    -0.76
     uVar
    -0.75
     AssemblyCulture
    -0.75
    SpringRunner
    -0.74
     المعيارى
    -0.73
     تعدى
    -0.73
    POSITIVE LOGITS
     transfer
    0.64
    Transfer
    0.57
    transfer
    0.56
     Transfer
    0.56
     afternoon
    0.49
    いよいよ
    0.49
     lunch
    0.48
     continue
    0.48
     optional
    0.47
    Approx
    0.47
    Act Density 0.059%

    No Known Activations