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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or inclusion among groups

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

    among a group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <!--
    -0.36
    complexContent
    -0.35
    HandlerContext
    -0.35
     Sche
    -0.34
     calça
    -0.34
    Sche
    -0.34
    DEB
    -0.34
    EventData
    -0.34
    rítica
    -0.34
     boyunca
    -0.34
    POSITIVE LOGITS
     among
    1.01
    among
    0.90
     Among
    0.84
     AMONG
    0.83
     parmi
    0.82
    Among
    0.81
     Parmi
    0.68
     amongst
    0.68
    Parmi
    0.66
    Среди
    0.63
    Act Density 0.006%

    No Known Activations