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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores

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

    menu items and logging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.89
    featureID
    -0.84
     autorytatywna
    -0.82
     ſche
    -0.76
    ſelf
    -0.73
    RTEE
    -0.73
     betweenstory
    -0.73
    ſelves
    -0.72
    AISSEE
    -0.72
     houſe
    -0.70
    POSITIVE LOGITS
    MouseAdapter
    0.35
    AlterField
    0.35
     only
    0.35
     مشارکت‌کنندگان
    0.33
     was
    0.33
     slightly
    0.33
    _
    0.32
     Sachen
    0.31
     very
    0.29
     went
    0.28
    Act Density 0.108%

    No Known Activations