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

    Neuronpedia

    INDEX
    Explanations

    connections between different concepts or ideas within textual data

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

    French text, often containing "ca"

    np_acts-logits-general · gemini-2.0-flash

    "ca" followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desiring
    -0.57
    ोंने
    -0.57
    vited
    -0.55
     disponibilités
    -0.54
    aware
    -0.53
     wishing
    -0.51
    writeFieldEnd
    -0.51
    طيع
    -0.51
     Aware
    -0.50
     fontsize
    -0.50
    POSITIVE LOGITS
     is
    0.65
    帖最后由
    0.64
     belongs
    0.64
     belong
    0.64
     αποτε
    0.60
     entail
    0.57
     comprises
    0.57
     comprise
    0.56
     represent
    0.55
     represents
    0.54
    Act Density 0.042%

    No Known Activations