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

    Neuronpedia

    INDEX
    Explanations

    technical terminologies related to electrical engineering concepts

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

    duos, twins, and partners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الدراسه
    -0.51
    𑄣
    -0.50
    انيف
    -0.48
     Weiſe
    -0.47
     (;;
    -0.47
    𑄠
    -0.47
    𑄮
    -0.47
    𑄪
    -0.47
    leiding
    -0.47
    <unused47>
    -0.47
    POSITIVE LOGITS
     duo
    0.50
     twin
    0.49
    ViewImports
    0.48
     twins
    0.47
    Twins
    0.44
     partner
    0.44
    Partner
    0.42
     partnership
    0.42
    LabelTagHelper
    0.39
    twin
    0.38
    Act Density 0.178%

    No Known Activations