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

    Neuronpedia

    INDEX
    Explanations

    elements related to connections and relationships within a dataset or analysis

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

    all three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.54
     Fourteen
    -0.52
    Fifth
    -0.51
    Sixth
    -0.50
     يتيمه
    -0.48
     Fifth
    -0.48
    httphttps
    -0.48
    Aholisi
    -0.47
     Sixteen
    -0.47
    -0.46
    POSITIVE LOGITS
     three
    2.05
     trio
    1.88
    three
    1.80
     trois
    1.67
     üç
    1.64
    Three
    1.61
     drei
    1.61
     ketiga
    1.55
     Three
    1.55
    三个
    1.52
    Act Density 1.010%

    No Known Activations