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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating collective effort or teamwork

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

    we or our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.52
     ujednoznacz
    -0.52
    AccessFile
    -0.50
     surla
    -0.47
    Personendaten
    -0.46
    vocable
    -0.46
     calloc
    -0.46
    sizeCache
    -0.45
     kasarigan
    -0.45
    rungsseite
    -0.45
    POSITIVE LOGITS
     lacked
    0.44
    ENCIES
    0.41
    ptos
    0.40
     lacking
    0.40
     practised
    0.39
    новништво
    0.39
     bäst
    0.39
     للاسماء
    0.38
     zijne
    0.38
    Configuration
    0.38
    Act Density 0.008%

    No Known Activations