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

    Neuronpedia

    INDEX
    Explanations

    mentions of injuries and physical conditions, particularly related to joints

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

    body part injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.81
    awtextra
    -0.74
    NameInMap
    -0.72
    ロウィン
    -0.71
     <<<<<<<<<<<<<<
    -0.68
    脚注の使い方
    -0.67
     surla
    -0.66
     ब्रेकडाउन
    -0.65
     ExecuteAsync
    -0.62
    Sucesor
    -0.62
    POSITIVE LOGITS
     izquierdo
    0.27
     devenu
    0.26
     underwent
    0.26
     hiciera
    0.26
     sostenibilidad
    0.26
    KERNEL
    0.25
     masculina
    0.25
     gué
    0.25
     furent
    0.24
     semaines
    0.24
    Act Density 0.016%

    No Known Activations