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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate regulatory compliance and performance metrics

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

    class athletes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     espalda
    -0.37
     vocación
    -0.36
     intptr
    -0.36
    Tē
    -0.35
    ต่อไป
    -0.35
     agresión
    -0.35
     ilusión
    -0.35
     lesión
    -0.35
    kosti
    -0.35
     pasión
    -0.35
    POSITIVE LOGITS
    HandlerContext
    0.57
     MenuView
    0.51
    ACI
    0.51
    akir
    0.50
     Kira
    0.49
     nahilalakip
    0.49
     snippetHide
    0.49
    afat
    0.48
    ESOME
    0.48
    HasAnnotation
    0.48
    Act Density 0.283%

    No Known Activations