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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or terms in a document

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

    pronouns and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BufferException
    -0.71
    MessageTagHelper
    -0.66
    AsUp
    -0.63
    سطس
    -0.57
    URLException
    -0.57
    makeText
    -0.57
    GEBURTSDATUM
    -0.57
    bitat
    -0.56
     onBind
    -0.56
    Gön
    -0.55
    POSITIVE LOGITS
     them
    0.55
     őket
    0.48
    them
    0.47
     dalamnya
    0.45
    她們
    0.44
    ándolos
    0.43
    arlos
    0.42
     onları
    0.42
     him
    0.41
     להם
    0.40
    Act Density 0.039%

    No Known Activations